Paper Citation Record · LEDGER

Beyond Jailbreaks: Revealing Stealthier and Broader LLM Security Risks Stemming from Alignment Failures

As of 9 August 2026, this Paper Citation Record lists 48 of 48 outbound references and 1 inbound Pith citation observation for arXiv:2506.07402.

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

pith.paper-citation-record.v1
2506.07402 v1

Coverage vector

measured 48 of 48 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T05:40:20.752585Z

measured 49 of 49 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-09T06:31:02.800959+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-01T18:55:03.319920Z

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

48 of 48 outbound references displayed

verified exact1
verified fuzzy9
unresolved38
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 7ac0cda6-c77c-48c6-99e7-985e17627304 · outbound

This paper cites Universal language model fine-tuning for text classifica- tion, 2018.

Beyond Jailbreaks: Revealing Stealthier and Broader LLM Security Risks Stemming from Alignment Failures Universal language model fine-tuning for text classifica- tion, 2018

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:40:21.505766Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 7a8c6123-ac07-45b4-aaef-ea22fed4a683 · outbound

This paper cites Training language models to follow instructions with human feedback.

Beyond Jailbreaks: Revealing Stealthier and Broader LLM Security Risks Stemming from Alignment Failures Training language models to follow instructions with human feedback

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-07T05:40:20.519392Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d7e06a19-25a4-49ea-9cf4-46033b91e68d · outbound

This paper cites Scaling instruction-finetuned language models.

Beyond Jailbreaks: Revealing Stealthier and Broader LLM Security Risks Stemming from Alignment Failures Scaling instruction-finetuned language models

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T05:40:20.525164Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f687c9cc-53af-4811-acf1-5026fc9bf588 · outbound

This paper cites Fine-Tuning Language Models from Human Preferences.

Beyond Jailbreaks: Revealing Stealthier and Broader LLM Security Risks Stemming from Alignment Failures Fine-Tuning Language Models from Human Preferences

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T05:40:20.529978Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6938c8e7-dd8a-473b-a01a-e7b0717c189e · outbound

This paper cites Direct preference optimization: Your language model is secretly a reward model.

Beyond Jailbreaks: Revealing Stealthier and Broader LLM Security Risks Stemming from Alignment Failures Direct preference optimization: Your language model is secretly a reward model

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T05:40:20.535236Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation be8403d9-f7ee-4916-a14e-cf1608a7fa44 · outbound

This paper cites Jailbreakchat.com, 2023.

Beyond Jailbreaks: Revealing Stealthier and Broader LLM Security Risks Stemming from Alignment Failures Jailbreakchat.com, 2023

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:40:21.439636Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation f6ff2025-0476-4e55-9c57-d49f5a91cb13 · outbound

This paper cites Jailbroken: How does llm safety training fail? Advances in Neural Information Processing Systems, 36:80079–80110, 2023.

Beyond Jailbreaks: Revealing Stealthier and Broader LLM Security Risks Stemming from Alignment Failures Jailbroken: How does llm safety training fail? Advances in Neural Information Processing Systems, 36:80079–80110, 2023

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T05:40:20.545428Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2f1a9f34-036d-4335-8a32-9f3ab8954e01 · outbound

This paper cites Are aligned neural networks adversarially aligned? Advances in Neural Information Processing Systems, 36:61478– 61500, 2023.

Beyond Jailbreaks: Revealing Stealthier and Broader LLM Security Risks Stemming from Alignment Failures Are aligned neural networks adversarially aligned? Advances in Neural Information Processing Systems, 36:61478– 61500, 2023

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:40:21.415500Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation bd3b9ee6-56ab-4793-ba5a-dc13d7fd6fcf · outbound

This paper cites do anything now.

Beyond Jailbreaks: Revealing Stealthier and Broader LLM Security Risks Stemming from Alignment Failures do anything now

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T05:40:20.555354Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a1753045-f0d9-442a-aecf-64ed9abd11ff · outbound

This paper cites Don’t listen to me: understanding and exploring jailbreak prompts of large language models.

Beyond Jailbreaks: Revealing Stealthier and Broader LLM Security Risks Stemming from Alignment Failures Don’t listen to me: understanding and exploring jailbreak prompts of large language models

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:40:21.390445Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation ac5bca8e-c73d-4f9e-90ca-fa8bed0495f8 · outbound

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

Beyond Jailbreaks: Revealing Stealthier and Broader LLM Security Risks Stemming from Alignment Failures Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T05:40:20.565977Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 36c6d1dc-e66c-4e72-868b-e30305efdd7a · outbound

This paper cites Jailbreaking Black Box Large Language Models in Twenty Queries.

Beyond Jailbreaks: Revealing Stealthier and Broader LLM Security Risks Stemming from Alignment Failures Jailbreaking Black Box Large Language Models in Twenty Queries

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T05:40:20.570649Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7d463ea2-dc58-4f1d-b807-d3b19f063b03 · outbound

This paper cites Tree of attacks: Jailbreaking black-box llms automatically.Advances in Neural Information Processing Systems, 37:61065–61105, 2024.

Beyond Jailbreaks: Revealing Stealthier and Broader LLM Security Risks Stemming from Alignment Failures Tree of attacks: Jailbreaking black-box llms automatically.Advances in Neural Information Processing Systems, 37:61065–61105, 2024

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T05:40:20.575426Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ff06be60-b1ab-4ac7-b4c7-f3d678f2af6b · outbound

This paper cites MasterKey: Automated Jailbreak Across Multiple Large Language Model Chatbots.

Beyond Jailbreaks: Revealing Stealthier and Broader LLM Security Risks Stemming from Alignment Failures MasterKey: Automated Jailbreak Across Multiple Large Language Model Chatbots

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T05:40:20.580018Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation afa7ba33-3fe7-41de-877d-2461d41a0ce3 · outbound

This paper cites Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks.

Beyond Jailbreaks: Revealing Stealthier and Broader LLM Security Risks Stemming from Alignment Failures Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T05:40:20.585362Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d202259b-976c-48e2-8129-af12e45802bc · outbound

This paper cites AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models.

Beyond Jailbreaks: Revealing Stealthier and Broader LLM Security Risks Stemming from Alignment Failures AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T05:40:20.590342Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation da3d46d1-a7b7-4829-a1a1-a80d0775e3ca · outbound

This paper cites AutoDAN: Interpretable Gradient-Based Adversarial Attacks on Large Language Models.

Beyond Jailbreaks: Revealing Stealthier and Broader LLM Security Risks Stemming from Alignment Failures AutoDAN: Interpretable Gradient-Based Adversarial Attacks on Large Language Models

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T05:40:20.595942Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8cd526e5-5d8d-4e82-91ab-2b9b4db91aa4 · outbound

This paper cites Catastrophic Jailbreak of Open-source LLMs via Exploiting Generation.

Beyond Jailbreaks: Revealing Stealthier and Broader LLM Security Risks Stemming from Alignment Failures Catastrophic Jailbreak of Open-source LLMs via Exploiting Generation

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T05:40:20.601664Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 595452c4-6357-4760-8f52-30d432d8a57b · outbound

This paper cites Weak-to-Strong Jailbreaking on Large Language Models.

Beyond Jailbreaks: Revealing Stealthier and Broader LLM Security Risks Stemming from Alignment Failures Weak-to-Strong Jailbreaking on Large Language Models

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T05:40:20.606600Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 81904555-64f5-41c7-a0fe-bfecc3e67c03 · outbound

This paper cites AdvPrompter: Fast Adaptive Adversarial Prompting for LLMs.

Beyond Jailbreaks: Revealing Stealthier and Broader LLM Security Risks Stemming from Alignment Failures AdvPrompter: Fast Adaptive Adversarial Prompting for LLMs

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T05:40:20.611175Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 72aa392a-d53a-4eb3-8989-88f9158796ad · outbound

This paper cites Improved Techniques for Optimization-Based Jailbreaking on Large Language Models.

Beyond Jailbreaks: Revealing Stealthier and Broader LLM Security Risks Stemming from Alignment Failures Improved Techniques for Optimization-Based Jailbreaking on Large Language Models

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T05:40:20.616360Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 72ba783a-5b5a-4037-a109-1035b69cdfe8 · outbound

This paper cites Don't Say No: Jailbreaking LLM by Suppressing Refusal.

Beyond Jailbreaks: Revealing Stealthier and Broader LLM Security Risks Stemming from Alignment Failures Don't Say No: Jailbreaking LLM by Suppressing Refusal

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T05:40:20.621417Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 95cbf8a9-6f0a-4ea8-b67d-d55cec96b58f · outbound

This paper cites AmpleGCG: Learning a Universal and Transferable Generative Model of Adversarial Suffixes for Jailbreaking Both Open and Closed LLMs.

Beyond Jailbreaks: Revealing Stealthier and Broader LLM Security Risks Stemming from Alignment Failures AmpleGCG: Learning a Universal and Transferable Generative Model of Adversarial Suffixes for Jailbreaking Both Open and Closed LLMs

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T05:40:20.626685Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 37d45666-6cd8-4238-a472-ce1bc8adba7e · outbound

This paper cites AutoDAN-Turbo: A Lifelong Agent for Strategy Self-Exploration to Jailbreak LLMs.

Beyond Jailbreaks: Revealing Stealthier and Broader LLM Security Risks Stemming from Alignment Failures AutoDAN-Turbo: A Lifelong Agent for Strategy Self-Exploration to Jailbreak LLMs

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T05:40:20.632046Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7d542fe5-5475-47de-b4ff-013c8b89ec90 · outbound

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

Beyond Jailbreaks: Revealing Stealthier and Broader LLM Security Risks Stemming from Alignment Failures Jailbreak Attacks and Defenses Against Large Language Models: A Survey

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-07T05:40:20.636809Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9bcc24c3-5661-475e-b745-7e0a568132f8 · outbound

This paper cites Llm jailbreak attack versus defense techniques–a comprehensive study.

Beyond Jailbreaks: Revealing Stealthier and Broader LLM Security Risks Stemming from Alignment Failures Llm jailbreak attack versus defense techniques–a comprehensive study

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:40:21.365440Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation ec8ff256-1793-4bab-b989-42bd5d49e3b0 · outbound

This paper cites LLM-Safety Evaluations Lack Robustness.

Beyond Jailbreaks: Revealing Stealthier and Broader LLM Security Risks Stemming from Alignment Failures LLM-Safety Evaluations Lack Robustness

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-07T05:40:20.646900Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b2eaf344-2622-4f66-b217-4850c0eb5904 · outbound

This paper cites JailbreakRadar: Comprehensive Assessment of Jailbreak Attacks Against LLMs.

Beyond Jailbreaks: Revealing Stealthier and Broader LLM Security Risks Stemming from Alignment Failures JailbreakRadar: Comprehensive Assessment of Jailbreak Attacks Against LLMs

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T05:40:20.651700Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f20d886e-3a37-4af6-864a-5e093bcc8e5e · outbound

This paper cites Sg-bench: Evaluating llm safety generalization across diverse tasks and prompt types.

Beyond Jailbreaks: Revealing Stealthier and Broader LLM Security Risks Stemming from Alignment Failures Sg-bench: Evaluating llm safety generalization across diverse tasks and prompt types

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:40:21.349668Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation ebeab4e4-5f8f-4310-a1ba-9de7ff330d25 · outbound

This paper cites JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models.

Beyond Jailbreaks: Revealing Stealthier and Broader LLM Security Risks Stemming from Alignment Failures JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-07T05:40:20.661675Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 51c51fb7-d940-44ea-83c4-8445e1beb86d · outbound

This paper cites JailbreakEval: An Integrated Toolkit for Evaluating Jailbreak Attempts Against Large Language Models.

Beyond Jailbreaks: Revealing Stealthier and Broader LLM Security Risks Stemming from Alignment Failures JailbreakEval: An Integrated Toolkit for Evaluating Jailbreak Attempts Against Large Language Models

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-07T05:40:20.666525Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3f30fa75-a85a-42b8-b79d-0bb40852e600 · outbound

This paper cites Clas 2024: The competition for llm and agent safety.

Beyond Jailbreaks: Revealing Stealthier and Broader LLM Security Risks Stemming from Alignment Failures Clas 2024: The competition for llm and agent safety

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:40:21.333247Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 7db82a51-965f-4deb-8037-686fccefef3d · outbound

This paper cites A StrongREJECT for Empty Jailbreaks.

Beyond Jailbreaks: Revealing Stealthier and Broader LLM Security Risks Stemming from Alignment Failures A StrongREJECT for Empty Jailbreaks

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-07T05:40:20.676687Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 606f5adb-80f0-41a5-8703-0e69f61b6ff6 · outbound

This paper cites The art of saying no: Contextual noncompliance in language models.

Beyond Jailbreaks: Revealing Stealthier and Broader LLM Security Risks Stemming from Alignment Failures The art of saying no: Contextual noncompliance in language models

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-07T05:40:20.682110Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 931ffb9d-d955-4d82-b723-9b4705eebfc9 · outbound

This paper cites How johnny can persuade llms to jailbreak them: Rethinking persuasion to challenge ai safety by humanizing llms.

Beyond Jailbreaks: Revealing Stealthier and Broader LLM Security Risks Stemming from Alignment Failures How johnny can persuade llms to jailbreak them: Rethinking persuasion to challenge ai safety by humanizing llms

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:40:21.307575Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation a0dc3ecf-570a-4d1e-ae01-7785e1e52f36 · outbound

This paper cites Jailbreaking large language models with symbolic mathematics, 2024.

Beyond Jailbreaks: Revealing Stealthier and Broader LLM Security Risks Stemming from Alignment Failures Jailbreaking large language models with symbolic mathematics, 2024

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:40:21.291327Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 5b995f12-018a-4ea8-83a6-6fbb92a7a99d · outbound

This paper cites GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts.

Beyond Jailbreaks: Revealing Stealthier and Broader LLM Security Risks Stemming from Alignment Failures GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-07T05:40:20.696608Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 34268b1e-ffbf-4159-9ee4-6aeecca7a4bf · outbound

This paper cites Prefill-level Jailbreak: A Black-Box Risk Analysis of Large Language Models.

Beyond Jailbreaks: Revealing Stealthier and Broader LLM Security Risks Stemming from Alignment Failures Prefill-level Jailbreak: A Black-Box Risk Analysis of Large Language Models

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-07T05:40:20.701570Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 37041393-4ed4-4b92-a263-8c859f7bd858 · outbound

This paper cites Rethinking How to Evaluate Language Model Jailbreak.

Beyond Jailbreaks: Revealing Stealthier and Broader LLM Security Risks Stemming from Alignment Failures Rethinking How to Evaluate Language Model Jailbreak

Reference 39

Resolution: verified exact; local_arxiv, observed 2026-08-07T05:40:20.926237Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 2a7751e3-04d6-4088-b57d-1229ae8704ae · outbound

This paper cites SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal.

Beyond Jailbreaks: Revealing Stealthier and Broader LLM Security Risks Stemming from Alignment Failures SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-07T05:40:20.711744Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a1070a30-5b1e-4ab6-992e-ec2f7ad6ff83 · outbound

This paper cites The Jailbreak Tax: How Useful are Your Jailbreak Outputs?.

Beyond Jailbreaks: Revealing Stealthier and Broader LLM Security Risks Stemming from Alignment Failures The Jailbreak Tax: How Useful are Your Jailbreak Outputs?

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-07T05:40:20.716732Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 26835b23-1641-4939-ab42-09bdb134a4a5 · outbound

This paper cites AIR-Bench 2024: A Safety Benchmark Based on Risk Categories from Regulations and Policies.

Beyond Jailbreaks: Revealing Stealthier and Broader LLM Security Risks Stemming from Alignment Failures AIR-Bench 2024: A Safety Benchmark Based on Risk Categories from Regulations and Policies

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-07T05:40:20.722684Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2912aaeb-2854-4b65-8fa6-47bfc05b8e3b · outbound

This paper cites Multimodal Situational Safety.

Beyond Jailbreaks: Revealing Stealthier and Broader LLM Security Risks Stemming from Alignment Failures Multimodal Situational Safety

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-07T05:40:20.727309Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b139af91-eb49-41c9-8e53-aad5732b7f87 · outbound

This paper cites Mmlu-pro: A more robust and challenging multi-task language understanding benchmark.

Beyond Jailbreaks: Revealing Stealthier and Broader LLM Security Risks Stemming from Alignment Failures Mmlu-pro: A more robust and challenging multi-task language understanding benchmark

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-07T05:40:20.732373Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 19b5f8c9-896d-4480-b287-6ebff5ed5fad · outbound

This paper cites TruthfulQA: Measuring How Models Mimic Human Falsehoods.

Beyond Jailbreaks: Revealing Stealthier and Broader LLM Security Risks Stemming from Alignment Failures TruthfulQA: Measuring How Models Mimic Human Falsehoods

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-07T05:40:20.737235Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d8e565ca-a31a-48a8-acc5-b88382c9daf0 · outbound

This paper cites Model Context Protocol (MCP): Landscape, Security Threats, and Future Research Directions.

Beyond Jailbreaks: Revealing Stealthier and Broader LLM Security Risks Stemming from Alignment Failures Model Context Protocol (MCP): Landscape, Security Threats, and Future Research Directions

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-07T05:40:20.742100Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f9ee1f79-47cb-4735-aa43-bfa24bca4413 · outbound

This paper cites Multilingual Jailbreak Challenges in Large Language Models.

Beyond Jailbreaks: Revealing Stealthier and Broader LLM Security Risks Stemming from Alignment Failures Multilingual Jailbreak Challenges in Large Language Models

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-07T05:40:20.747279Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c549df12-5d4b-49ff-9913-808afde46e72 · outbound

This paper cites Safety Alignment Should Be Made More Than Just a Few Tokens Deep.

Beyond Jailbreaks: Revealing Stealthier and Broader LLM Security Risks Stemming from Alignment Failures Safety Alignment Should Be Made More Than Just a Few Tokens Deep

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-07T05:40:20.752585Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 394b7429-0807-402b-917e-b5967f811225 · inbound

How Jailbreak Attacks Inform Safety Alignment: A Defender-Centric, Shapley-Based Evaluation of Jailbreak Contributions cites this paper.

How Jailbreak Attacks Inform Safety Alignment: A Defender-Centric, Shapley-Based Evaluation of Jailbreak Contributions Beyond Jailbreaks: Revealing Stealthier and Broader LLM Security Risks Stemming from Alignment Failures

Reference 131

Resolution: unresolved; no resolver link, observed 2026-08-01T18:55:03.319920Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.