Paper Citation Record · LEDGER

Attacking LLMs and AI Agents: Advertisement Embedding Attacks Against Large Language Models

As of 18 August 2026, this Paper Citation Record lists 39 of 39 outbound references and 0 inbound Pith citation observations for arXiv:2508.17674.

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

pith.paper-citation-record.v1
2508.17674 v2

Coverage vector

measured 39 of 39 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-15T17:06:09.003652Z

measured 39 of 39 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-17T06:30:58.91139+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

39 of 39 outbound references displayed

verified exact0
verified fuzzy0
unresolved39
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation a2b61f2e-dd63-456d-8654-e60897578326 · outbound

This paper cites Language models are few-shot learners,.

Attacking LLMs and AI Agents: Advertisement Embedding Attacks Against Large Language Models Language models are few-shot learners,

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-15T17:06:08.725427Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b2325057-d3f5-47d9-880b-ee806dfbda5f · outbound

This paper cites On the Opportunities and Risks of Foundation Models.

Attacking LLMs and AI Agents: Advertisement Embedding Attacks Against Large Language Models On the Opportunities and Risks of Foundation Models

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-15T17:06:08.732532Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7640f49f-2074-4465-bca2-aba9d6e1a756 · outbound

This paper cites Sparks of Artificial General Intelligence: Early experiments with GPT-4.

Attacking LLMs and AI Agents: Advertisement Embedding Attacks Against Large Language Models Sparks of Artificial General Intelligence: Early experiments with GPT-4

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-15T17:06:08.738933Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 26080ef8-3fb1-42a5-82c9-f4b2ef05a622 · outbound

This paper cites LLaMA: Open and Efficient Foundation Language Models.

Attacking LLMs and AI Agents: Advertisement Embedding Attacks Against Large Language Models LLaMA: Open and Efficient Foundation Language Models

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-15T17:06:08.747077Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7788d717-67c2-4ed9-8674-7066cac99a7f · outbound

This paper cites Soull- mate: An application enhancing diverse mental health support with adaptive llms, prompt engineering, and rag techniques,.

Attacking LLMs and AI Agents: Advertisement Embedding Attacks Against Large Language Models Soull- mate: An application enhancing diverse mental health support with adaptive llms, prompt engineering, and rag techniques,

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-15T17:06:08.753632Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 057784fb-9d1d-478e-bc3f-44eeb6c8a15b · outbound

This paper cites Soullmate: An adaptive llm-driven system for advanced mental health support and assessment, based on a systematic application survey,.

Attacking LLMs and AI Agents: Advertisement Embedding Attacks Against Large Language Models Soullmate: An adaptive llm-driven system for advanced mental health support and assessment, based on a systematic application survey,

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-15T17:06:08.759569Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a7d41ebb-cbe8-43ee-aa2b-3cc33bb46ee0 · outbound

This paper cites A layered multi-expert framework for long-context mental health assessments,.

Attacking LLMs and AI Agents: Advertisement Embedding Attacks Against Large Language Models A layered multi-expert framework for long-context mental health assessments,

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-15T17:06:08.765653Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 11977003-975c-449f-9b20-f275c6605097 · outbound

This paper cites Advancing mental health pre-screening: A new custom gpt for psychological distress assessment,.

Attacking LLMs and AI Agents: Advertisement Embedding Attacks Against Large Language Models Advancing mental health pre-screening: A new custom gpt for psychological distress assessment,

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-15T17:06:08.772645Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b8b2126a-001f-4279-bede-a570a1d349b5 · outbound

This paper cites Chatdoctor: A medical chat model fine-tuned on a large language model meta-ai (llama) using medical domain knowledge,.

Attacking LLMs and AI Agents: Advertisement Embedding Attacks Against Large Language Models Chatdoctor: A medical chat model fine-tuned on a large language model meta-ai (llama) using medical domain knowledge,

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-15T17:06:08.781389Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 27f7bc2f-e47c-4ee0-a128-eb6d52b936ac · outbound

This paper cites LLM Online Spatial-temporal Signal Reconstruction Under Noise.

Attacking LLMs and AI Agents: Advertisement Embedding Attacks Against Large Language Models LLM Online Spatial-temporal Signal Reconstruction Under Noise

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-15T17:06:08.787070Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 79e0d6d7-e99f-4936-a9b1-a713e8fac8d4 · outbound

This paper cites Explaining and Harnessing Adversarial Examples.

Attacking LLMs and AI Agents: Advertisement Embedding Attacks Against Large Language Models Explaining and Harnessing Adversarial Examples

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-15T17:06:08.796083Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 471c9fd8-aeae-49e3-bfa0-9889119d101e · outbound

This paper cites BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain.

Attacking LLMs and AI Agents: Advertisement Embedding Attacks Against Large Language Models BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-15T17:06:08.803161Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 41b84694-01aa-4414-9a25-5a1ff15ab8bc · outbound

This paper cites Membership inference attacks against machine learning models,.

Attacking LLMs and AI Agents: Advertisement Embedding Attacks Against Large Language Models Membership inference attacks against machine learning models,

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-15T17:06:08.811352Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0c298087-073b-4df3-9cb9-cf1f38017d33 · outbound

This paper cites Stealing machine learning models via prediction APIs,.

Attacking LLMs and AI Agents: Advertisement Embedding Attacks Against Large Language Models Stealing machine learning models via prediction APIs,

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-15T17:06:08.817686Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 02011c41-4532-45fa-9e94-3d3073c99147 · outbound

This paper cites Weight Poisoning Attacks on Pre-trained Models.

Attacking LLMs and AI Agents: Advertisement Embedding Attacks Against Large Language Models Weight Poisoning Attacks on Pre-trained Models

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-15T17:06:08.823092Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b80cd584-0c40-48be-a578-a78e8c036c51 · outbound

This paper cites Huynh and J.

Attacking LLMs and AI Agents: Advertisement Embedding Attacks Against Large Language Models Huynh and J

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-15T17:06:08.831362Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 54e9b452-bd43-4a2f-afa7-80b0194f7eaf · outbound

This paper cites Poisonprompt: Backdoor attack on prompt- based large language models,.

Attacking LLMs and AI Agents: Advertisement Embedding Attacks Against Large Language Models Poisonprompt: Backdoor attack on prompt- based large language models,

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-15T17:06:08.839934Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f2497ce0-96b9-4101-872d-3b0787379db7 · outbound

This paper cites Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training.

Attacking LLMs and AI Agents: Advertisement Embedding Attacks Against Large Language Models Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-15T17:06:08.848335Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 60d01c43-bdfe-40b7-8994-bf2d71875010 · outbound

This paper cites Membership inference attacks on machine learning: a survey,.

Attacking LLMs and AI Agents: Advertisement Embedding Attacks Against Large Language Models Membership inference attacks on machine learning: a survey,

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-15T17:06:08.855694Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aa11fcdc-3776-460e-a9da-09124201d424 · outbound

This paper cites A survey on membership inference attacks and defenses in machine learning,.

Attacking LLMs and AI Agents: Advertisement Embedding Attacks Against Large Language Models A survey on membership inference attacks and defenses in machine learning,

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-15T17:06:08.861466Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ac7d38ae-00e1-4fa2-94d1-5596edac40c9 · outbound

This paper cites I know what you trained last summer: A survey on stealing machine learning models and defences,.

Attacking LLMs and AI Agents: Advertisement Embedding Attacks Against Large Language Models I know what you trained last summer: A survey on stealing machine learning models and defences,

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-15T17:06:08.868145Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ca336346-cb25-49e4-bb9e-38cf699380f6 · outbound

This paper cites Sok: All you need to know about on-device ml model extraction-the gap between research and practice,.

Attacking LLMs and AI Agents: Advertisement Embedding Attacks Against Large Language Models Sok: All you need to know about on-device ml model extraction-the gap between research and practice,

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-15T17:06:08.879574Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4726218e-7e4e-4f88-80d3-af42f1adf87b · outbound

This paper cites Intriguing properties of neural networks.

Attacking LLMs and AI Agents: Advertisement Embedding Attacks Against Large Language Models Intriguing properties of neural networks

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-15T17:06:08.888145Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a9369774-23a7-4342-972c-331384011a36 · outbound

This paper cites Robust physical-world attacks on deep learning visual classification,.

Attacking LLMs and AI Agents: Advertisement Embedding Attacks Against Large Language Models Robust physical-world attacks on deep learning visual classification,

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-15T17:06:08.896392Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bd597678-dc29-45f0-bc7e-4dba55b085b3 · outbound

This paper cites DARTS: Deceiving Autonomous Cars with Toxic Signs.

Attacking LLMs and AI Agents: Advertisement Embedding Attacks Against Large Language Models DARTS: Deceiving Autonomous Cars with Toxic Signs

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-15T17:06:08.906325Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fbac02a9-e894-473c-ada8-d9615a21b212 · outbound

This paper cites Trojaning attack on neural networks,.

Attacking LLMs and AI Agents: Advertisement Embedding Attacks Against Large Language Models Trojaning attack on neural networks,

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-15T17:06:08.913566Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 38808ae0-148b-42df-887a-35fd2633a4d1 · outbound

This paper cites Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning.

Attacking LLMs and AI Agents: Advertisement Embedding Attacks Against Large Language Models Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-15T17:06:08.919800Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 74a9ac8b-61b9-410d-af7f-7c8f72acacc5 · outbound

This paper cites The secret sharer: Evaluating and testing unintended memorization in neural networks,.

Attacking LLMs and AI Agents: Advertisement Embedding Attacks Against Large Language Models The secret sharer: Evaluating and testing unintended memorization in neural networks,

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-15T17:06:08.927844Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e77e7502-615e-473e-98c3-9d78ad8a0762 · outbound

This paper cites Scalable Extraction of Training Data from (Production) Language Models.

Attacking LLMs and AI Agents: Advertisement Embedding Attacks Against Large Language Models Scalable Extraction of Training Data from (Production) Language Models

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-15T17:06:08.934584Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a9bb2a80-dec6-4688-8cca-ebf2baae0950 · outbound

This paper cites A survey on evaluation of large language models,.

Attacking LLMs and AI Agents: Advertisement Embedding Attacks Against Large Language Models A survey on evaluation of large language models,

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-15T17:06:08.941514Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0ea083d4-6141-44e2-8203-878395e43fb3 · outbound

This paper cites Universal and Transferable Adversarial Attacks on Aligned Language Models.

Attacking LLMs and AI Agents: Advertisement Embedding Attacks Against Large Language Models Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-15T17:06:08.949106Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 21fd57f3-5298-476c-bb37-fa29b200f333 · outbound

This paper cites Adversarial Training for Large Neural Language Models.

Attacking LLMs and AI Agents: Advertisement Embedding Attacks Against Large Language Models Adversarial Training for Large Neural Language Models

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-15T17:06:08.957836Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bcfcc478-0126-4475-9449-61e7a215df19 · outbound

This paper cites Jailbroken: How does llm safety training fail?.

Attacking LLMs and AI Agents: Advertisement Embedding Attacks Against Large Language Models Jailbroken: How does llm safety training fail?

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-15T17:06:08.963710Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 87ffcd33-4a32-4053-be3c-df9d34ca7bd5 · outbound

This paper cites Jailbreaking ChatGPT via Prompt Engineering: An Empirical Study.

Attacking LLMs and AI Agents: Advertisement Embedding Attacks Against Large Language Models Jailbreaking ChatGPT via Prompt Engineering: An Empirical Study

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-15T17:06:08.971742Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0ba70b2d-b6bc-498c-a350-a75fc477a1c2 · outbound

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

Attacking LLMs and AI Agents: Advertisement Embedding Attacks Against Large Language Models Not what you’ve signed up for: Compromising real-world llm-integrated applications with indirect prompt injection,

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-15T17:06:08.977940Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3088c257-1149-40af-93a6-4d66a4c75fb4 · outbound

This paper cites Online display ad- vertising markets: A literature review and future directions,.

Attacking LLMs and AI Agents: Advertisement Embedding Attacks Against Large Language Models Online display ad- vertising markets: A literature review and future directions,

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-15T17:06:08.983134Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 54ffbcd3-3ba9-45c9-8994-228470822c66 · outbound

This paper cites The dark alleys of madison avenue: Understanding malicious advertisements,.

Attacking LLMs and AI Agents: Advertisement Embedding Attacks Against Large Language Models The dark alleys of madison avenue: Understanding malicious advertisements,

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-15T17:06:08.988850Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 92c4b772-f5af-4961-b565-20ad6b345983 · outbound

This paper cites How to backdoor federated learning,.

Attacking LLMs and AI Agents: Advertisement Embedding Attacks Against Large Language Models How to backdoor federated learning,

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-15T17:06:08.994366Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b6e7e95c-4594-4bc2-b73f-d587272028bc · outbound

This paper cites Badnl: Backdoor attacks against nlp models with semantic- preserving improvements,.

Attacking LLMs and AI Agents: Advertisement Embedding Attacks Against Large Language Models Badnl: Backdoor attacks against nlp models with semantic- preserving improvements,

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-15T17:06:09.003652Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.