Pith. sign in

Paper Citation Record · LEDGER

Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search

As of 15 August 2026, this Paper Citation Record lists 100 of 102 outbound references and 3 inbound Pith citation observations for arXiv:2502.04951.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2502.04951 v3

Coverage vector

measured 100 of 102 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-08T20:57:43.713954Z

measured 103 of 103 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-15T06:32:42.880941+00:00

measured 3 of 3 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-05-25T03:09:59.710039Z

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: arxiv_reference, observed 2026-05-25T03:10:16.809113Z

Reference resolution

100 of 102 outbound references displayed

  • verified exact2
  • verified fuzzy49
  • unresolved48
  • parse uncertain1
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 898bd2b6-4e33-414d-9bc8-724b607e8194 · outbound

This paper cites https://chat.openai.com/, 2025.

Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search https://chat.openai.com/, 2025

Reference 1

Resolution
unresolved
no resolver link, observed 2026-08-08T20:57:43.308805Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-08T20:57:43.308805Z digest=sha256:5e1d99fe98806cf68f30b704d7bd4047544c0e989d144f0f09b1cf5bbaab446f

Observation 707d991b-9887-4f82-be96-e3beacb0621e · outbound

This paper cites https://checkphish.bolster.ai/, 2025.

Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search https://checkphish.bolster.ai/, 2025

Reference 2

Resolution
unresolved
no resolver link, observed 2026-08-08T20:57:43.315167Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-08T20:57:43.315167Z digest=sha256:5c534debb1220bc2b53076f702511615a552a6f9797bc236df69a31e1e1daa65

Observation bd292d28-94e8-4f04-8930-9bb3d62fd732 · outbound

This paper cites https://www.doubao.com/, 2025.

Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search https://www.doubao.com/, 2025

Reference 3

Resolution
unresolved
no resolver link, observed 2026-08-08T20:57:43.319815Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-08T20:57:43.319815Z digest=sha256:2c2d2ad9b9b7886903217a6acf5a76e44b35a7106347a394ce990c3828cd3016

Observation 975e7e90-90ac-44ca-b538-d4a4f6906e3c · outbound

This paper cites https://www.google.com/, 2025.

Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search https://www.google.com/, 2025

Reference 4

Resolution
unresolved
no resolver link, observed 2026-08-08T20:57:43.324280Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-08T20:57:43.324280Z digest=sha256:587a1fe95d9e5882f11401eabfb54ea9df32be5b8991b644d103a0fa092b3f56

Observation 353dc71d-fa9c-4e57-a0c0-243fe4a02997 · outbound

This paper cites https://trends.google.com/ trends/, 2025.

Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search https://trends.google.com/ trends/, 2025

Reference 5

Resolution
unresolved
no resolver link, observed 2026-08-08T20:57:43.328805Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-08T20:57:43.328805Z digest=sha256:1333d0cb7cf530265c3c16e5b82c06f3e81bcbcdb5a75ca0801d368e0e32f2de

Observation 15e3eb14-34c1-461e-8ee1-5c95e3ea8768 · outbound

This paper cites https://x.ai/grok, 2025.

Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search https://x.ai/grok, 2025

Reference 6

Resolution
unresolved
no resolver link, observed 2026-08-08T20:57:43.333185Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-08T20:57:43.333185Z digest=sha256:7aca70392b72dfe55c31a1feb6f778f36248fe8e6b82bfe00d060bb48ce7a365

Observation 742ca265-8524-4a87-a18f-2fc74c6debfc · outbound

This paper cites https://kimi.moonshot.cn/, 2025.

Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search https://kimi.moonshot.cn/, 2025

Reference 7

Resolution
unresolved
no resolver link, observed 2026-08-08T20:57:43.338138Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-08T20:57:43.338138Z digest=sha256:0c8251c369c85a8e6c2673f77fa5d839eca6fdf9d0d9ee86a193c23bf612399c

Observation 47353eb3-9e35-4dff-b594-2d5d5c968b7a · outbound

This paper cites https://otx.alienvault.com/, 2025.

Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search https://otx.alienvault.com/, 2025

Reference 8

Resolution
unresolved
no resolver link, observed 2026-08-08T20:57:43.342387Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-08T20:57:43.342387Z digest=sha256:1ca16a0e414c259b303a59aa4baffbac03a799abf3c60e8d4f6608dd0cab00d3

Observation f3686bfd-bf44-454a-8835-2052b8da4b57 · outbound

This paper cites https://metamask.io/, 2025.

Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search https://metamask.io/, 2025

Reference 9

Resolution
unresolved
no resolver link, observed 2026-08-08T20:57:43.346444Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-08T20:57:43.346444Z digest=sha256:73cb9089ed1e7338f846f65bc379299ad50c19153505cdd5193256732cba44f9

Observation 54b442b5-81f0-4779-aefd-eaced35e98c0 · outbound

This paper cites https://www.bing.com/, 2025.

Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search https://www.bing.com/, 2025

Reference 10

Resolution
unresolved
no resolver link, observed 2026-08-08T20:57:43.350513Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-08T20:57:43.350513Z digest=sha256:65a843bf53e5a74376cd3d51e5d682d2d6eedff07db22bafb24fa1de03e91d26

Observation f57341b6-302a-4286-807d-a29ed3aef962 · outbound

This paper cites https://copilot.microsoft.

Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search https://copilot.microsoft

Reference 11

Resolution
unresolved
no resolver link, observed 2026-08-08T20:57:43.354477Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-08T20:57:43.354477Z digest=sha256:d01a119b14cb4bc12cc4cbe36c3690d3901ac40d05d3762137999c2fbdc5a53f

Observation e64996b5-a921-43fb-9e0b-0c3eff4472ee · outbound

This paper cites https://platform.openai.com/docs/ models/, 2025.

Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search https://platform.openai.com/docs/ models/, 2025

Reference 12

Resolution
unresolved
no resolver link, observed 2026-08-08T20:57:43.358160Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-08T20:57:43.358160Z digest=sha256:30cee621bc4f4c41297982159aba894fe46737307e0788d91dcccc4dc083350d

Observation d4f65d4c-1f98-4a34-89fc-fd238505ed55 · outbound

This paper cites https://www.perplexity.ai/, 2025.

Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search https://www.perplexity.ai/, 2025

Reference 13

Resolution
unresolved
no resolver link, observed 2026-08-08T20:57:43.361748Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-08T20:57:43.361748Z digest=sha256:3e4c821eeefe804b4e4fc31eaa41191797756398035f79b070e3b5faae374040

Observation cbb6e491-e5f3-4e63-b131-d9faf39aa977 · outbound

This paper cites https://phishtank.com/, 2025.

Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search https://phishtank.com/, 2025

Reference 14

Resolution
unresolved
no resolver link, observed 2026-08-08T20:57:43.365527Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-08T20:57:43.365527Z digest=sha256:bd25f97d12856ea453745ece323b1749ac30614a3a3d1db708dcf536041fba39

Observation 35704046-3256-4b77-b136-2ebe12f7d4da · outbound

This paper cites https://www.quora.com/, 2025.

Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search https://www.quora.com/, 2025

Reference 15

Resolution
unresolved
no resolver link, observed 2026-08-08T20:57:43.369407Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-08T20:57:43.369407Z digest=sha256:52105370f92a646a20c2f220e7762bb0c3ffad55ae9560a30d1b6104e6ef904e

Observation d6f9d5a5-f4ee-4974-b8a9-e7138ab60994 · outbound

This paper cites https://www.scamadviser.com/, 2025.

Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search https://www.scamadviser.com/, 2025

Reference 16

Resolution
unresolved
no resolver link, observed 2026-08-08T20:57:43.373155Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-08T20:57:43.373155Z digest=sha256:90911ff8d47f6b3b59cc86b818630e8b8bcf223fccd223aaac32004e93f9e701

Observation 5ec666c1-838e-4a03-87ba-401ec687f3a6 · outbound

This paper cites https://www.surbl.org/surbl-analysis/ lookup, 2025.

Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search https://www.surbl.org/surbl-analysis/ lookup, 2025

Reference 17

Resolution
unresolved
no resolver link, observed 2026-08-08T20:57:43.376858Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-08T20:57:43.376858Z digest=sha256:eac3bc587544cb2228f0ae230d60ab2adf0e58e86f70cceca83f0c33103cec52

Observation 099c4f4b-2590-4670-8870-3aed9a9803e5 · outbound

This paper cites https://app.textcortex.com/, 2025.

Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search https://app.textcortex.com/, 2025

Reference 18

Resolution
unresolved
no resolver link, observed 2026-08-08T20:57:43.380518Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-08T20:57:43.380518Z digest=sha256:5a6dd702ea60b2c9b2796f608cc623bcd9047c2ec802d88627a7da84f89e2d98

Observation 0d530701-3437-43fa-a0db-b0537786127e · outbound

This paper cites https://x.threatbook.com/, 2025.

Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search https://x.threatbook.com/, 2025

Reference 19

Resolution
unresolved
no resolver link, observed 2026-08-08T20:57:43.384377Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-08T20:57:43.384377Z digest=sha256:08ded5299a6346761f1e82e08166d3f55401d3c30de83b6341f4f1a313a4359a

Observation 61f13988-d148-4894-82d5-b2ccf182ac34 · outbound

This paper cites https://www.wikipedia.org/, 2025.

Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search https://www.wikipedia.org/, 2025

Reference 20

Resolution
unresolved
no resolver link, observed 2026-08-08T20:57:43.387970Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-08T20:57:43.387970Z digest=sha256:b24ac46243e8882b5290f9bafb19da3df26e900baf6c139544d52003dfb5e174

Observation 4f1fc4f2-b616-43da-adeb-0e7aceb98c2d · outbound

This paper cites https://x.com/, 2025.

Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search https://x.com/, 2025

Reference 21

Resolution
parse uncertain
no resolver link, observed 2026-08-08T20:57:43.391862Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-08T20:57:43.391862Z digest=sha256:02e0d69fa20edb14f22e201e60e0958d39e2f8fcc0d8dcc74f78336c12e09017

Observation d3e206aa-51b7-4925-9df3-7f5d880fd9a1 · outbound

This paper cites Visualphishnet: Zero-day phishing website detection by visual similarity.

Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search Visualphishnet: Zero-day phishing website detection by visual similarity

Reference 22

Resolution
unresolved
no resolver link, observed 2026-08-08T20:57:43.395789Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-08T20:57:43.395789Z digest=sha256:bbc7826df95906aa964769f2c3a6c0ef203bb9dbcdf9270991d6230464e2c00b

Observation 7c07afa3-7b78-4a09-880d-71943bf241fa · outbound

This paper cites Phishing attacks detection using machine learning approach.

Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search Phishing attacks detection using machine learning approach

Reference 23

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T20:57:45.142263Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-08T20:57:43.399873Z digest=sha256:71a6d88a77fe39b81ad704ff39d02798c96bca66b1de9005a4565be3d788c7cf

Observation 1541d079-477f-452c-82a6-cfc109827064 · outbound

This paper cites A survey of intelligent detection designs of html url phishing attacks.

Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search A survey of intelligent detection designs of html url phishing attacks

Reference 24

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T20:57:45.128284Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-08T20:57:43.403865Z digest=sha256:d54728575c3f1510ac0ba33cd0bb58e2042c4994d243d379a371faa92b0885dd

Observation ee9ac716-c78b-4486-aefb-7b0c2b97b452 · outbound

This paper cites A survey of url-based phishing detection.

Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search A survey of url-based phishing detection

Reference 25

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T20:57:45.113174Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-08T20:57:43.407663Z digest=sha256:6c6f9c8c092f19c847c10c185dc2417caae43aa0a337030bb7fc543db081799e

Observation afe93cbc-f010-4823-bb18-63512915c929 · outbound

This paper cites Language models are few-shot learners.

Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search Language models are few-shot learners

Reference 26

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T20:57:45.098136Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-08T20:57:43.411377Z digest=sha256:63e308362bcb82dcd13095dcd7c5f7151f5fa96e537b43eb3b28bd6a817dc257

Observation 9396343f-4595-4168-b946-e061f00c359f · outbound

This paper cites Xgboost: A scal- able tree boosting system.

Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search Xgboost: A scal- able tree boosting system

Reference 27

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T20:57:45.083656Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-08T20:57:43.415322Z digest=sha256:4c678ba222b51026211fd18e035fdd40fd71c3fcd9efd2671de4b499e80c5f05

Observation 5ac5dd6b-8dd1-4f83-bbd8-90ec25ef1c92 · outbound

This paper cites TrojanRAG: Retrieval-Augmented Generation Can Be Backdoor Driver in Large Language Models.

Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search TrojanRAG: Retrieval-Augmented Generation Can Be Backdoor Driver in Large Language Models

Reference 28

Resolution
unresolved
no resolver link, observed 2026-08-08T20:57:43.419115Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-08T20:57:43.419115Z digest=sha256:8cfda352a48f77a2171ec802afe24c471aed1c2fb961c00ca7176ed28b2f66bd

Observation 7b42186d-5d0c-4cda-834c-b22da834504a · outbound

This paper cites Weighted kappa: Nominal scale agree- ment provision for scaled disagreement or partial credit.

Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search Weighted kappa: Nominal scale agree- ment provision for scaled disagreement or partial credit

Reference 29

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T20:57:45.069315Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-08T20:57:43.423254Z digest=sha256:454f724b02dcfc6b105a164b806dfe173438f6f41f65788f60a4111567cb23f2

Observation 53f49bb9-8540-4aed-8de9-a97d8abc7b26 · outbound

This paper cites Llm-based edge intelligence: A com- prehensive survey on architectures, applications, secu- rity and trustworthiness.

Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search Llm-based edge intelligence: A com- prehensive survey on architectures, applications, secu- rity and trustworthiness

Reference 30

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T20:57:45.055046Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-08T20:57:43.427200Z digest=sha256:b30fa7a29a9213857abc5a5b50342e42337f50e6e721956de1e4b356fb79c088

Observation 4f2836e4-0324-40a1-87db-814a8365b25a · outbound

This paper cites Retrieval-Augmented Generation for Large Language Models: A Survey.

Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search Retrieval-Augmented Generation for Large Language Models: A Survey

Reference 31

Resolution
unresolved
no resolver link, observed 2026-08-08T20:57:43.430984Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-08T20:57:43.430984Z digest=sha256:eaf9474d572b87b5452b1ed408f3ad3bc54a7822184d6a01ab88a9e8590587c1

Observation 8231307f-370e-4cd2-9f7f-e9de51d90e1f · outbound

This paper cites What is perplexity pro? https://www.perplexity.ai/help-center/en/ articles/10352901-what-is-perplexity-pro , 2025.

Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search What is perplexity pro? https://www.perplexity.ai/help-center/en/ articles/10352901-what-is-perplexity-pro , 2025

Reference 32

Resolution
verified exact
raw_fallback, observed 2026-08-08T20:57:44.233557Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-08T20:57:43.434988Z digest=sha256:21b5209cc7bfc0f30edbce6e024526ce35d7d6467412c55a790c6c8d13aa1c6a

Observation e4799705-8f12-4ea2-891f-be902ad48093 · outbound

This paper cites Safety misalignment against large language models.

Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search Safety misalignment against large language models

Reference 33

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T20:57:45.041705Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-08T20:57:43.438796Z digest=sha256:009627a08c20ce75eb8bf798cc5d9e99cea57cd8421b4962e05d7e7a62bf45c6

Observation da3cabd1-47f2-4366-91b6-400e2656eb2e · outbound

This paper cites Not what you’ve signed up for: Compromising real-world llm-integrated applications with indirect prompt injec- tion.

Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search Not what you’ve signed up for: Compromising real-world llm-integrated applications with indirect prompt injec- tion

Reference 34

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T20:57:45.028496Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-08T20:57:43.442440Z digest=sha256:ca01dfb8d4520f1af7d17231d2b0a6a609efad1f4354c71e437cf035fe485c61

Observation 9fa4fa75-8c8e-4a89-a526-117fda84c86c · outbound

This paper cites Artificial intelligence security and privacy: a survey.Sci- ence China Information Sciences, 2025.

Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search Artificial intelligence security and privacy: a survey.Sci- ence China Information Sciences, 2025

Reference 35

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T20:57:45.014337Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-08T20:57:43.446385Z digest=sha256:c1f6ecb2fdedb1fff38d2b84909a5103a7fe16ec6998939390a147da72f49e72

Observation 2f5de104-60e3-4a0e-98f6-10d10cb1eed4 · outbound

This paper cites an unresolved cited work.

Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search Unresolved cited work

Reference 36

Resolution
unresolved
raw_fallback, observed 2026-08-08T20:57:45.000354Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-08T20:57:43.450114Z digest=sha256:4924a75be49d11ed001de27196768a613b74e7d57ef000aa2843e17cf6ab475e

Observation 2ce236ea-cdfc-45d9-afbe-c8e1320e2eef · outbound

This paper cites Survey of hallucination in natural language generation.

Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search Survey of hallucination in natural language generation

Reference 37

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T20:57:44.986329Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-08T20:57:43.454015Z digest=sha256:9f7e7173223b240bf3dd0860ec99eeb93ea5a4ca6dc50738156ea000d2ba4e19

Observation 0e5233b7-5d3a-46c0-8d9a-695cfc4b4d9b · outbound

This paper cites Phishing webpage detection: Unveiling the threat land- scape and investigating detection techniques.

Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search Phishing webpage detection: Unveiling the threat land- scape and investigating detection techniques

Reference 38

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T20:57:44.971288Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-08T20:57:43.457888Z digest=sha256:b9ab4e55a06c1e7e070c5b0163474694f86b4fd77aa971d80c235157494be158

Observation 6f1d9587-67e2-4071-a1e9-4a00441e843f · outbound

This paper cites The measurement of observer agreement for categorical data.

Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search The measurement of observer agreement for categorical data

Reference 39

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T20:57:44.956674Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-08T20:57:43.461558Z digest=sha256:af92dc34d903b9609576be6bc7b8efacd6d95e520a79a6437a544e41a55274ac

Observation 187687e9-8d38-444a-9715-97937e4550bf · outbound

This paper cites URLNet: Learning a URL Representation with Deep Learning for Malicious URL Detection.

Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search URLNet: Learning a URL Representation with Deep Learning for Malicious URL Detection

Reference 40

Resolution
unresolved
no resolver link, observed 2026-08-08T20:57:43.465798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-08T20:57:43.465798Z digest=sha256:2371295887098e4c602ae57212151c81e88f0f05d686e0b2f4ade793c54249d2

Observation ece254ef-5935-47a8-9ce0-77d0b353b8d0 · outbound

This paper cites Retrieval-augmented generation for knowledge-intensive nlp tasks.

Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search Retrieval-augmented generation for knowledge-intensive nlp tasks

Reference 41

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T20:57:44.942672Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-08T20:57:43.470373Z digest=sha256:68a21d6f207e7a3f8f56341aa856da467b794369c0d1449cc7bbef0cee7484ea

Observation 9164ebcd-dc2b-4946-a490-b5ca605593df · outbound

This paper cites Phishpedia: A hybrid deep learning based approach to visually identify phishing webpages.

Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search Phishpedia: A hybrid deep learning based approach to visually identify phishing webpages

Reference 42

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T20:57:44.928693Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-08T20:57:43.474774Z digest=sha256:b72cb7193e56e1671e4197c8fbf08251178d75687a583ae1e7e08fcc45855b34

Observation b6e60825-d0af-458b-a0a7-21d089009536 · outbound

This paper cites Less defined knowl- edge and more true alarms: Reference-based phishing detection without a pre-defined reference list.

Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search Less defined knowl- edge and more true alarms: Reference-based phishing detection without a pre-defined reference list

Reference 43

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T20:57:44.913110Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-08T20:57:43.480277Z digest=sha256:4080ee3082438774f48c3c1e614bfc62dc6ef08ba37f1c0d17fd842cb7bb4ab8

Observation 28ba13d0-b6b0-4036-b65e-ffacd82bc6a3 · outbound

This paper cites Inferring phishing intention via webpage appearance and dynam- ics: A deep vision based approach.

Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search Inferring phishing intention via webpage appearance and dynam- ics: A deep vision based approach

Reference 44

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T20:57:44.896872Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-08T20:57:43.484636Z digest=sha256:8ee52c42434514a1fff95dc48c099d04de18d4a686ee07c518f2cebb738b0229

Observation 4e27f4c2-676e-4012-9ade-1c690c0c6c55 · outbound

This paper cites Automatic and Universal Prompt Injection Attacks against Large Language Models.

Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search Automatic and Universal Prompt Injection Attacks against Large Language Models

Reference 45

Resolution
unresolved
no resolver link, observed 2026-08-08T20:57:43.488821Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-08T20:57:43.488821Z digest=sha256:4f1d1697c90511eb038776ffeebf05a5bd452a7c32f6d93a3c6dc61f565b9317

Observation d6b70b97-688d-42a1-a6f8-1a5af3205360 · outbound

This paper cites Quantized Delta Weight Is Safety Keeper.

Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search Quantized Delta Weight Is Safety Keeper

Reference 46

Resolution
unresolved
no resolver link, observed 2026-08-08T20:57:43.493412Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-08T20:57:43.493412Z digest=sha256:352c1e6f6112de19d73ee33ae0f893178bae249653abf2bb50a1ad4564f3e42b

Observation 241ae5c1-707f-4d79-9f3b-cfd55a6867f1 · outbound

This paper cites Saul, Stefan Savage, and Geof- frey M.

Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search Saul, Stefan Savage, and Geof- frey M

Reference 47

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T20:57:44.881495Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-08T20:57:43.499013Z digest=sha256:5342a15f5ea2df239629df5ef14550ce45fcf6702f81be585a63a6719bd06339

Observation 20de46c2-d8c5-499f-b087-103ea73c8f2d · outbound

This paper cites Intelligent Semantic Web Search Engines: A Brief Survey.

Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search Intelligent Semantic Web Search Engines: A Brief Survey

Reference 48

Resolution
verified exact
local_arxiv, observed 2026-08-08T20:57:44.101862Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-08T20:57:43.503089Z digest=sha256:84daa19e6db94611cc3e300a6a0d86de1d36a00227db62ddd50e393f1d39b507

Observation f63b65a9-cced-4276-898c-80eeb8e795c6 · outbound

This paper cites Ghorbani.

Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search Ghorbani

Reference 49

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T20:57:44.866370Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-08T20:57:43.507207Z digest=sha256:07bd31ac67e37f5dce0aab2e964aff6a10b08e36179f101245f68c656a602b4f

Observation 461db5a3-b76e-4f36-851b-a4311b23eb2e · outbound

This paper cites Phishing-alarm: Robust and efficient phishing detection via page component similarity.

Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search Phishing-alarm: Robust and efficient phishing detection via page component similarity

Reference 50

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T20:57:44.852641Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-08T20:57:43.510945Z digest=sha256:3ccaea1b35a9f0da27eaf3e3b816b0e0a561d92a8f2644c9af22371009b5cd7d

Observation bcd1841b-7b9b-49fe-889b-4f0e417a6390 · outbound

This paper cites Visual-similarity-based phishing detection.

Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search Visual-similarity-based phishing detection

Reference 51

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T20:57:44.837753Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-08T20:57:43.514755Z digest=sha256:cf580af3db2378707c4b54e4449e8823149b2ea5e11531b06880469e7f040c00

Observation 497a8595-ecbb-4de9-835b-a42fcede5934 · outbound

This paper cites The Llama 3 Herd of Models.

Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search The Llama 3 Herd of Models

Reference 52

Resolution
unresolved
no resolver link, observed 2026-08-08T20:57:43.518386Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-08T20:57:43.518386Z digest=sha256:b3957d0f6b39a6187305691af70b583fe59c262d9e2d20f9782618335957eda6

Observation c2b34cd0-1d93-4f09-8b81-912b7c9da2c2 · outbound

This paper cites Adversarial Search Engine Optimization for Large Language Models.

Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search Adversarial Search Engine Optimization for Large Language Models

Reference 53

Resolution
unresolved
no resolver link, observed 2026-08-08T20:57:43.522329Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-08T20:57:43.522329Z digest=sha256:c6633e6a10d41af0d07c274bb452b2e78420dd18103ba66579ec71f457306b9a

Observation b21d8a80-fc67-4fce-b6c9-ed19e26bb126 · outbound

This paper cites Investigating LLM Applications in E-Commerce.

Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search Investigating LLM Applications in E-Commerce

Reference 54

Resolution
unresolved
no resolver link, observed 2026-08-08T20:57:43.526395Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-08T20:57:43.526395Z digest=sha256:05e2b00001d985c0f129c3f997c8394215f267a1e4f15a524390739926774ae8

Observation ca384b86-44e2-43e8-bb81-9d5e7d2d6e68 · outbound

This paper cites Jalmbench: Benchmark- ing jailbreak vulnerabilities in audio language models.

Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search Jalmbench: Benchmark- ing jailbreak vulnerabilities in audio language models

Reference 55

Resolution
unresolved
no resolver link, observed 2026-08-08T20:57:43.530388Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-08T20:57:43.530388Z digest=sha256:db0eabab0da0ace7427da3e9b2f4a818040956d16b5fd743c400a5945fe2d454

Observation 744b5ab6-9e0d-4de8-aadf-3b4830d6298a · outbound

This paper cites Ignore previous prompt: Attack techniques for language models.

Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search Ignore previous prompt: Attack techniques for language models

Reference 56

Resolution
unresolved
no resolver link, observed 2026-08-08T20:57:43.534240Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-08T20:57:43.534240Z digest=sha256:82517a4f29beb0ab11f9c894bee8c879411ece1572decace49a6553a84a948a5

Observation 72cf1db4-feb5-42c8-836d-0bceba8915c5 · outbound

This paper cites Detec- tion of phishing websites using an efficient feature-based machine learning framework.

Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search Detec- tion of phishing websites using an efficient feature-based machine learning framework

Reference 57

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T20:57:44.812984Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-08T20:57:43.538156Z digest=sha256:72fff06ad728e5cef268890b761ded75d2e6bf2b6f2e5a3fbe1d15cec657bcda

Observation a318998e-0524-4168-a3ce-b148861781df · outbound

This paper cites A brief review on search engine optimization.

Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search A brief review on search engine optimization

Reference 58

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T20:57:44.799813Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-08T20:57:43.542322Z digest=sha256:fd85f0239193e52118a7d4dfa7ec14d61cc9f2b7df7c4d5e8fe5a07b2a712593

Observation 1e6e3a5d-fef0-4ff6-8c5c-9ed3261c92f2 · outbound

This paper cites Somesha, Alwyn Roshan Pais, Routhu Srinivasa Rao, and Vikram Singh Rathour.

Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search Somesha, Alwyn Roshan Pais, Routhu Srinivasa Rao, and Vikram Singh Rathour

Reference 59

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T20:57:44.786674Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-08T20:57:43.546496Z digest=sha256:8c53bb1bd8ffeeb1089e384a447217e102800a7d7a7b101b5d6bf8d97e3aca5f

Observation f53aa59a-7139-4f6d-85f7-52159075e043 · outbound

This paper cites Rothschild, Daniel G.

Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search Rothschild, Daniel G

Reference 60

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T20:57:44.773714Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-08T20:57:43.550243Z digest=sha256:6473276787d29c4e74cad48ae9715d343b0e6de54586e08b2de6e804ff07363c

Observation 31f63575-9209-4aa1-b089-089200a2c28a · outbound

This paper cites A survey on semantic web search engine.

Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search A survey on semantic web search engine

Reference 61

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T20:57:44.760398Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-08T20:57:43.554368Z digest=sha256:b908068386d23dc73d7e59ffcc791497ea67caf2420d6fbc50255123e96b59ca

Observation 432ba8ad-b83f-4991-8766-3276148e5cf0 · outbound

This paper cites Peftguard: Detecting backdoor attacks against parameter-efficient fine-tuning.

Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search Peftguard: Detecting backdoor attacks against parameter-efficient fine-tuning

Reference 62

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T20:57:44.747581Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-08T20:57:43.558254Z digest=sha256:8880bfe6d8e14810acec39240568d026bfdcaebce1ccdd1ff07ce8de4fe04e40

Observation 6b306c5d-3278-4c30-8665-064781035636 · outbound

This paper cites Glue pizza and eat rocks - exploiting vulnerabilities in retrieval-augmented generative models.

Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search Glue pizza and eat rocks - exploiting vulnerabilities in retrieval-augmented generative models

Reference 63

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T20:57:44.734763Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-08T20:57:43.562209Z digest=sha256:8f04486575c829133b644f01ad76d3a800c85defb5c338aae1fec08e24e627d4

Observation 5239e70e-79c1-4205-b11b-9c0c99273e56 · outbound

This paper cites A compre- hensive survey on poisoning attacks and countermea- sures in machine learning.

Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search A compre- hensive survey on poisoning attacks and countermea- sures in machine learning

Reference 64

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T20:57:44.721356Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-08T20:57:43.566090Z digest=sha256:544d758dc3bffba8b1888a2e45ee1866260207bc1ad6f8ddafcd2c02ab321876

Observation 2621ea77-d6e7-4858-98de-294e0e2dca01 · outbound

This paper cites Creating large language model applications utilizing langchain: A primer on developing llm apps fast.International Con- ference on Applied Engineering and Natural Sciences, 2023.

Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search Creating large language model applications utilizing langchain: A primer on developing llm apps fast.International Con- ference on Applied Engineering and Natural Sciences, 2023

Reference 65

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T20:57:44.707380Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-08T20:57:43.569803Z digest=sha256:4f881f415daf78a895153c8ae007cba00175c0f7ae4345dbff069fbb98c0faf4

Observation f3fcc5b5-0bc2-4157-bc41-07aadfb88e74 · outbound

This paper cites Hunting malicious tls certificates with deep neural networks.

Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search Hunting malicious tls certificates with deep neural networks

Reference 66

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T20:57:44.692596Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-08T20:57:43.573546Z digest=sha256:27a9b6c0977f7665b3ab03e293b174f583ffb77ff8aa8a2a3189477819d4ee2b

Observation e9cc970b-4ea8-4d2c-8408-6fd7c5c8d1d7 · outbound

This paper cites Attention is all you need.

Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search Attention is all you need

Reference 67

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T20:57:44.677990Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-08T20:57:43.577640Z digest=sha256:6ad0fdbd263901f3a86c7fbec5e987bfd9c9d469ca64afe66df440e2db4e8c50

Observation 88ac13d6-ddce-4085-b9d5-13cddb052e12 · outbound

This paper cites Chain-of-thought prompting elicits reasoning in large language models.

Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search Chain-of-thought prompting elicits reasoning in large language models

Reference 68

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T20:57:44.662383Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-08T20:57:43.581485Z digest=sha256:aac7f301cb7033355fb41ff55bcabc667f6d048df9a5f5fd0b6509885322dc1a

Observation 94e24a9f-061c-4bcb-85b2-7f55be0e4ec0 · outbound

This paper cites AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation.

Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation

Reference 69

Resolution
unresolved
no resolver link, observed 2026-08-08T20:57:43.585304Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-08T20:57:43.585304Z digest=sha256:5bc85e7d2bd73b0e502f9cc062aa021e4c2d8fc8cb553ff13c2a37d1837bd38f

Observation 9e5df8e4-d61f-4874-9e44-da2ef5f942d4 · outbound

This paper cites A comprehensive study of jailbreak attack versus defense for large language models.

Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search A comprehensive study of jailbreak attack versus defense for large language models

Reference 70

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T20:57:44.648761Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-08T20:57:43.589513Z digest=sha256:a51315b1c2be456e3e2c1c0128bfcdd81c5454e210090913b3273582a9a96042

Observation d67bea61-0fbb-4b2e-8bdf-fc693e254edf · outbound

This paper cites ReAct: Synergizing Reasoning and Acting in Language Models.

Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search ReAct: Synergizing Reasoning and Acting in Language Models

Reference 71

Resolution
unresolved
no resolver link, observed 2026-08-08T20:57:43.593279Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-08T20:57:43.593279Z digest=sha256:e9c31a218477f48b012f2349db9fcc36658a06b5b6dd473483a2117eb812a55d

Observation 42ef0b05-c04d-4001-969d-0ea98f067224 · outbound

This paper cites Data poisoning attacks against machine learning algorithms.

Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search Data poisoning attacks against machine learning algorithms

Reference 72

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T20:57:44.634916Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-08T20:57:43.597854Z digest=sha256:76cfeb500fff18ebf1a636ec900deb9c75836ca21411427f2f8d8f68c0e698dd

Observation 8bcc4d61-5791-4f0f-9293-c6aa22d3d377 · outbound

This paper cites Benchmarking and Defending Against Indirect Prompt Injection Attacks on Large Language Models.

Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search Benchmarking and Defending Against Indirect Prompt Injection Attacks on Large Language Models

Reference 73

Resolution
unresolved
no resolver link, observed 2026-08-08T20:57:43.602204Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-08T20:57:43.602204Z digest=sha256:4dbdabdda7b789e628629b453582830d77d520d7aa2652f0bc7fd7af74cc5483

Observation 14a2e49c-b973-413f-abd0-857e3691e2a6 · outbound

This paper cites Jailbreak Attacks and Defenses Against Large Language Models: A Survey.

Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search Jailbreak Attacks and Defenses Against Large Language Models: A Survey

Reference 74

Resolution
unresolved
no resolver link, observed 2026-08-08T20:57:43.606806Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-08T20:57:43.606806Z digest=sha256:694b46e41cc6703491f43d66c373aaf506913d4da5fa85a2494032757fb4a1bf

Observation 5dc885e7-71d5-41fa-aa77-466f672738cb · outbound

This paper cites Fc-attack: Jailbreaking large vision-language models via auto-generated flowcharts.

Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search Fc-attack: Jailbreaking large vision-language models via auto-generated flowcharts

Reference 75

Resolution
unresolved
no resolver link, observed 2026-08-08T20:57:43.611542Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-08T20:57:43.611542Z digest=sha256:1da92ab122b2fefe3f5fbb9940c70905428f1c3f08ebc3fc7833f0b52381d557

Observation 383d3700-170e-4f16-b0fd-f78cf81365da · outbound

This paper cites Cl-attack: Textual backdoor attacks via cross-lingual triggers.

Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search Cl-attack: Textual backdoor attacks via cross-lingual triggers

Reference 76

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T20:57:44.621021Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-08T20:57:43.615830Z digest=sha256:058a52685abcb2fe52226be30b6e6813cfda407695ebafa663f06d52bdb4363a

Observation 62f9c640-e219-46b4-8fc4-3b33bdfd1938 · outbound

This paper cites Phishing or not phishing? a survey on the detection of phishing websites.

Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search Phishing or not phishing? a survey on the detection of phishing websites

Reference 77

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T20:57:44.606878Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-08T20:57:43.620025Z digest=sha256:8421309463719589a8d6870896f7cb6382de33113d34617e5803092b611b6432

Observation c4987acd-3e48-4441-91f7-83a942ae0d80 · outbound

This paper cites PoisonedRAG: Knowledge Corruption Attacks to Retrieval-Augmented Generation of Large Language Models.

Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search PoisonedRAG: Knowledge Corruption Attacks to Retrieval-Augmented Generation of Large Language Models

Reference 78

Resolution
unresolved
no resolver link, observed 2026-08-08T20:57:43.624290Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-08T20:57:43.624290Z digest=sha256:3d88346b4f95e5507ce6f6d1c939f7e9740ec596a81fb3544bc990f3ef861f24

Observation 8434ba1f-9c1d-4ad5-a7e0-954f060d3032 · outbound

This paper cites Telegram official app.

Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search Telegram official app

Reference 79

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T20:57:44.593479Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-08T20:57:43.629037Z digest=sha256:6d1b1b8d21e3ebd70aedb33b2bb840d4887ccee743680adca58feb6e3b349f7e

Observation ba6ea44c-f960-4289-9f77-1decdac9c143 · outbound

This paper cites get-rich- quick.

Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search get-rich- quick

Reference 80

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T20:57:44.580052Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-08T20:57:43.633220Z digest=sha256:73686aa8d6a0d487ca6c633e9d0451879d33276137ee8503f816c84ac82dd6a8

Observation 87d699bc-4e0d-4437-aacb-05e3ca98d100 · outbound

This paper cites While not always harmful, it can clutter inboxes, waste time, and sometimes lead to phishing or other malicious activities.

Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search While not always harmful, it can clutter inboxes, waste time, and sometimes lead to phishing or other malicious activities

Reference 81

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T20:57:44.566741Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-08T20:57:43.637276Z digest=sha256:6e4df1f3ae7f76878f2d8dbeb9890f3b8186c9d3883e621b7f65a8a4144c2eb9

Observation e2bca547-dc7d-4482-a4c7-5a7585b1141f · outbound

This paper cites It is designed to mislead, manipulate public opinion, or generate traffic for financial or political gain.

Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search It is designed to mislead, manipulate public opinion, or generate traffic for financial or political gain

Reference 82

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T20:57:44.553281Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-08T20:57:43.641198Z digest=sha256:f17cc76ab77a5717df315193047a6639387f90ef48c31b99f7f95fe9ead77c44

Observation 58c81eb8-f2df-42b4-9b42-b07cf2fb1fc6 · outbound

This paper cites This website offers free gift cards but requires entering your credit card information.

Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search This website offers free gift cards but requires entering your credit card information

Reference 83

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T20:57:44.539712Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-08T20:57:43.645731Z digest=sha256:c685cfc30ed863494a4ffed7c1f9e5d9de3bf7c881ad2b4592cdf3c16d0a449a

Observation 5118e4fe-c999-4fff-8369-9dc2205dc71e · outbound

This paper cites - The URL offers free gift cards but requests credit card information, matching the definition of phishing.

Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search - The URL offers free gift cards but requests credit card information, matching the definition of phishing

Reference 84

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T20:57:44.526823Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-08T20:57:43.649774Z digest=sha256:74c7be24fe17c8b62ce77ddd97a4f5f739a201f1cc5f481e03e06e0e3b223256

Observation eb5b71dd-6f62-467a-8bdb-1e86439770c0 · outbound

This paper cites - The content explicitly asks for credit card information, fulfilling this indicator.

Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search - The content explicitly asks for credit card information, fulfilling this indicator

Reference 85

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T20:57:44.513242Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-08T20:57:43.654146Z digest=sha256:87443c479bc5387da1598e725e639f7e8cb5241d1e39f43ee492ec0e63742ab8

Observation 6f19cd75-631c-4b3a-94f4-6c63d7f62a76 · outbound

This paper cites an unresolved cited work.

Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search Unresolved cited work

Reference 86

Resolution
unresolved
raw_fallback, observed 2026-08-08T20:57:44.498737Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-08T20:57:43.658035Z digest=sha256:442ed3e8de80be6f48bbe2e347f555de89d75ffea30d97f46e0e36e2100c54c8

Observation eb87a942-cd18-4d18-b7e8-a4dec673ee06 · outbound

This paper cites The Earth will be invaded by aliens next week, claims a report.

Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search The Earth will be invaded by aliens next week, claims a report

Reference 87

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T20:57:44.484019Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-08T20:57:43.661758Z digest=sha256:26ed8f0aa3fd857fa63c6ef5ddf557ae3706a04593cde5ede12bb25ecbd26e3c

Observation 62c82a7c-5c41-4310-8d40-5d4a4337b372 · outbound

This paper cites - The content claims an alien invasion without credible evidence, fitting the definition of fake news.

Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search - The content claims an alien invasion without credible evidence, fitting the definition of fake news

Reference 88

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T20:57:44.469517Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-08T20:57:43.665651Z digest=sha256:355efb33e307f541f451c73cf83c39436d5e039b4edcc1c18eaeecd7b8f5a3a4

Observation e7d9a2e5-13e7-46b0-9976-ead87c099918 · outbound

This paper cites - The claim is sensationalized and unsupported by credible sources, meeting these indicators.

Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search - The claim is sensationalized and unsupported by credible sources, meeting these indicators

Reference 89

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T20:57:44.455690Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-08T20:57:43.669763Z digest=sha256:b67dc00c61f3a54dffb55fd81bde7f26356443d64823691cb8ea73e25f697741

Observation 84a9a3db-9755-4072-a4fd-b54f70e5e623 · outbound

This paper cites an unresolved cited work.

Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search Unresolved cited work

Reference 90

Resolution
unresolved
raw_fallback, observed 2026-08-08T20:57:44.442830Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-08T20:57:43.674075Z digest=sha256:694cd0b556d3719cb5b4eaae7ac6ea8e8d84977a39e35977b492ad4ffb25ca73

Observation 43845167-f867-49df-9dd5-ba4de9225d99 · outbound

This paper cites This website compiles open-access scientific papers for free download.

Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search This website compiles open-access scientific papers for free download

Reference 91

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T20:57:44.429579Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-08T20:57:43.679068Z digest=sha256:45e0fb354c329415a0ed6c896d137f47c2a2089d1baf2b16c727d62047a39983

Observation 4acb3901-2271-432c-a638-694002fd86d0 · outbound

This paper cites an unresolved cited work.

Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search Unresolved cited work

Reference 92

Resolution
unresolved
raw_fallback, observed 2026-08-08T20:57:44.416428Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-08T20:57:43.683657Z digest=sha256:7cefeef5a327f71461d3e686a3f940795b6dafcde4a4cea821d289fd54d7ca3c

Observation 45b714c6-7b64-4e24-978a-cb61c3273648 · outbound

This paper cites an unresolved cited work.

Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search Unresolved cited work

Reference 93

Resolution
unresolved
raw_fallback, observed 2026-08-08T20:57:44.403425Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-08T20:57:43.687477Z digest=sha256:17aa50ca6149d1db127feb297ca16e1dada1da42de0d2ddba38c8e2fcc5ee950

Observation 574386a7-c16d-416f-a3fd-1f59266f30d8 · outbound

This paper cites an unresolved cited work.

Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search Unresolved cited work

Reference 94

Resolution
unresolved
raw_fallback, observed 2026-08-08T20:57:44.389960Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-08T20:57:43.691191Z digest=sha256:5e1da2ad000a063d651258722ff8e846f81df3927364356b31dc4a992a393814

Observation 560c1331-0c4c-4abf-8c27-d262ae9feafb · outbound

This paper cites /” sep- arated) in the URL. Redirection: Detects if the URL contains unexpected redi- rection markers (e.g., “//.

Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search /” sep- arated) in the URL. Redirection: Detects if the URL contains unexpected redi- rection markers (e.g., “//

Reference 95

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T20:57:44.376712Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-08T20:57:43.694752Z digest=sha256:c37b18f1ef52fdaab75166ec89cdc7a773b34a168333b3ca87b62f8b4eb1f837

Observation c13b6b1d-9036-4bd6-ad85-b9c391898fac · outbound

This paper cites an unresolved cited work.

Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search Unresolved cited work

Reference 96

Resolution
unresolved
raw_fallback, observed 2026-08-08T20:57:44.362269Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-08T20:57:43.698587Z digest=sha256:73a5a75a4b66d253740a1515eefcae4e46cfda64c73b75ffd029b91d54eaf33a

Observation b9f411c8-7bc5-42e0-95a7-bfef2c0d2b54 · outbound

This paper cites an unresolved cited work.

Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search Unresolved cited work

Reference 97

Resolution
unresolved
raw_fallback, observed 2026-08-08T20:57:44.348836Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-08T20:57:43.702315Z digest=sha256:6005abd0c57cfde54999816a4ddbf787b788a35f1e87aa342f239231d91abb6e

Observation ff6c05b7-3ad0-49c2-a737-4460f0b48a22 · outbound

This paper cites an unresolved cited work.

Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search Unresolved cited work

Reference 98

Resolution
unresolved
raw_fallback, observed 2026-08-08T20:57:44.334693Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-08T20:57:43.706107Z digest=sha256:e74df8ccf7f8c5e9430cdb2555399e330378a34f231488068933fc0f9743d475

Observation 398d057e-e1b7-4039-b12e-49f852246c25 · outbound

This paper cites an unresolved cited work.

Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search Unresolved cited work

Reference 99

Resolution
unresolved
raw_fallback, observed 2026-08-08T20:57:44.321629Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-08T20:57:43.710144Z digest=sha256:e7fe36f05e97fb56cc13a9bfc6d69a1f0081d9f3843eb0c9cdb7ca56442b273d

Observation 659a3c95-3a1f-443d-b3ef-34114b6ad0a3 · outbound

This paper cites an unresolved cited work.

Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search Unresolved cited work

Reference 100

Resolution
unresolved
raw_fallback, observed 2026-08-08T20:57:44.307721Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-08T20:57:43.713954Z digest=sha256:af7427e7ca3ac18b6f6f649ad5050b7cf2c3fb4dd517efe35778c00d15200cf9

Pith citing papers

Observation 662b3739-e640-405a-b01f-e04529e1f58e · inbound

When Search Goes Wrong: Red-Teaming Web-Augmented Large Language Models cites this paper.

When Search Goes Wrong: Red-Teaming Web-Augmented Large Language Models Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search

Reference 26

Resolution
verified exact
arxiv_id, observed 2026-05-18T09:31:11.626255Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-05-18T09:29:14.842228Z digest=sha256:6d45cbc0213f8901003a362573db9f139b2ff886b421fe8f4a1d0202ad7a4bfa

Observation a51b35e1-c53d-4905-ab11-3a805fa62133 · inbound

PIIGuard: Mitigating PII Harvesting under Adversarial Sanitization cites this paper.

PIIGuard: Mitigating PII Harvesting under Adversarial Sanitization Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search

Reference 9

Resolution
verified exact
arxiv_id, observed 2026-05-11T17:11:15.272280Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-05-08T17:49:39.533090Z digest=sha256:391b16ef7ff5aa22f639c00ef8cacdcd65961d7804018fe80e8ba30ca09d7087

Observation f6a58ea5-a3d7-42d5-a8da-0c324b905f4c · inbound

Synthetic Sources?: Auditing Generative Search Engine Citations for Evidence of AI-Generated Sources cites this paper.

Synthetic Sources?: Auditing Generative Search Engine Citations for Evidence of AI-Generated Sources Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search

Reference 29

Resolution
verified exact
arxiv_id, observed 2026-05-25T03:10:16.811358Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-05-25T03:09:59.710039Z digest=sha256:800df0be9285f34465a8a5893b6516f929283a26bf49d122a95123524538dc3b