Paper Citation Record · LEDGER

"I am bad": Interpreting Stealthy, Universal and Robust Audio Jailbreaks in Audio-Language Models

As of 9 August 2026, this Paper Citation Record lists 59 of 59 outbound references and 7 inbound Pith citation observations for arXiv:2502.00718.

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

pith.paper-citation-record.v1
2502.00718 v2

Coverage vector

measured 59 of 59 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-09T18:05:52.411107Z

measured 66 of 66 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 7 of 7 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T15:42:19.934200Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-06-29T05:53:09.562517Z

Reference resolution

59 of 59 outbound references displayed

verified exact5
verified fuzzy3
unresolved51
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 7bf96aeb-feb5-4280-8404-bf68c1088b43 · outbound

This paper cites Flamingo: a Visual Language Model for Few-Shot Learning.

"I am bad": Interpreting Stealthy, Universal and Robust Audio Jailbreaks in Audio-Language Models Flamingo: a Visual Language Model for Few-Shot Learning

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-09T18:05:52.203599Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 61bfcb78-ce78-4d9c-b207-5cc8efc7610a · outbound

This paper cites Multimodal machine learning: A survey and taxonomy.

"I am bad": Interpreting Stealthy, Universal and Robust Audio Jailbreaks in Audio-Language Models Multimodal machine learning: A survey and taxonomy

Reference 2

Resolution: verified exact; arxiv_id_nonexistent, observed 2026-08-09T18:05:53.756582Z

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 dfce9281-ab22-4a5f-99a5-c5af9cb0dc71 · outbound

This paper cites Evasion Attacks against Machine Learning at Test Time, pp.\ 387–402.

"I am bad": Interpreting Stealthy, Universal and Robust Audio Jailbreaks in Audio-Language Models Evasion Attacks against Machine Learning at Test Time, pp.\ 387–402

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-09T18:05:52.212255Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 60f5044d-e729-40c0-8ba7-14f32dfddc2a · outbound

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

"I am bad": Interpreting Stealthy, Universal and Robust Audio Jailbreaks in Audio-Language Models On the Opportunities and Risks of Foundation Models

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-09T18:05:52.215894Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f1552174-b227-4c2e-801d-a2784d273df4 · outbound

This paper cites Language Models are Few-Shot Learners.

"I am bad": Interpreting Stealthy, Universal and Robust Audio Jailbreaks in Audio-Language Models Language Models are Few-Shot Learners

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-09T18:05:52.219800Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5c48a6cc-0341-4ca9-922d-1702d9882feb · outbound

This paper cites Audio Adversarial Examples: Targeted Attacks on Speech-to-Text.

"I am bad": Interpreting Stealthy, Universal and Robust Audio Jailbreaks in Audio-Language Models Audio Adversarial Examples: Targeted Attacks on Speech-to-Text

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-09T18:05:52.223609Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 910dba40-53d9-40fc-8903-a2de0d9c95e2 · outbound

This paper cites Are aligned neural networks adversarially aligned?.

"I am bad": Interpreting Stealthy, Universal and Robust Audio Jailbreaks in Audio-Language Models Are aligned neural networks adversarially aligned?

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-09T18:05:52.227708Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1d140a9d-87a8-4194-9922-066906d2cede · outbound

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

"I am bad": Interpreting Stealthy, Universal and Robust Audio Jailbreaks in Audio-Language Models JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-09T18:05:52.231429Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 21115587-0540-47a4-9271-0a6430d890cd · outbound

This paper cites BEATs: Audio Pre-Training with Acoustic Tokenizers.

"I am bad": Interpreting Stealthy, Universal and Robust Audio Jailbreaks in Audio-Language Models BEATs: Audio Pre-Training with Acoustic Tokenizers

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-09T18:05:52.235239Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a6ffa163-7034-41dc-b559-21894303ea0a · outbound

This paper cites E., Stoica, I., and Xing, E.

"I am bad": Interpreting Stealthy, Universal and Robust Audio Jailbreaks in Audio-Language Models E., Stoica, I., and Xing, E

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-09T18:05:52.240306Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 67f2d290-ed0e-4896-8685-b45fdb997948 · outbound

This paper cites Deep reinforcement learning from human preferences.

"I am bad": Interpreting Stealthy, Universal and Robust Audio Jailbreaks in Audio-Language Models Deep reinforcement learning from human preferences

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-09T18:05:52.243569Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f5448147-e2f0-4260-9b1d-48b69411d164 · outbound

This paper cites Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models.

"I am bad": Interpreting Stealthy, Universal and Robust Audio Jailbreaks in Audio-Language Models Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-09T18:05:52.247296Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation efa689ac-80a8-40e5-ae60-d1c2ecca8920 · outbound

This paper cites Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge.

"I am bad": Interpreting Stealthy, Universal and Robust Audio Jailbreaks in Audio-Language Models Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-09T18:05:52.251049Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4dd26791-469c-4111-b9a2-572703678f65 · outbound

This paper cites Pengi: An Audio Language Model for Audio Tasks.

"I am bad": Interpreting Stealthy, Universal and Robust Audio Jailbreaks in Audio-Language Models Pengi: An Audio Language Model for Audio Tasks

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-09T18:05:52.254541Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 72a3d137-feea-4b30-a407-aaad073858b8 · outbound

This paper cites HotFlip: White-Box Adversarial Examples for Text Classification.

"I am bad": Interpreting Stealthy, Universal and Robust Audio Jailbreaks in Audio-Language Models HotFlip: White-Box Adversarial Examples for Text Classification

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-09T18:05:52.258027Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cd6077ff-6625-4d13-8c08-909271d57e7b · outbound

This paper cites Physical Adversarial Examples for Object Detectors.

"I am bad": Interpreting Stealthy, Universal and Robust Audio Jailbreaks in Audio-Language Models Physical Adversarial Examples for Object Detectors

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-09T18:05:52.261748Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 95a03691-838c-4c02-834c-86d4e303c06b · outbound

This paper cites JailbreakLens: Visual Analysis of Jailbreak Attacks Against Large Language Models.

"I am bad": Interpreting Stealthy, Universal and Robust Audio Jailbreaks in Audio-Language Models JailbreakLens: Visual Analysis of Jailbreak Attacks Against Large Language Models

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-09T18:05:52.265466Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4f394338-d719-4066-b742-428d8b994608 · outbound

This paper cites Advddos: Zero-query adversarial attacks against commercial speech recognition systems.

"I am bad": Interpreting Stealthy, Universal and Robust Audio Jailbreaks in Audio-Language Models Advddos: Zero-query adversarial attacks against commercial speech recognition systems

Reference 18

Resolution: verified exact; arxiv_id_nonexistent, observed 2026-08-09T18:05:53.465045Z

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 890b2520-8524-4e34-ba4d-e2bb57660447 · outbound

This paper cites RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models.

"I am bad": Interpreting Stealthy, Universal and Robust Audio Jailbreaks in Audio-Language Models RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-09T18:05:52.272593Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ebf9c0f6-606f-4c82-9dd9-72356bae4ed4 · outbound

This paper cites and Unitary team.

"I am bad": Interpreting Stealthy, Universal and Robust Audio Jailbreaks in Audio-Language Models and Unitary team

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T18:05:53.807091Z

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 ba4f1ca4-fe9b-4438-9a3b-60cfda8044a0 · outbound

This paper cites Best-of-N Jailbreaking.

"I am bad": Interpreting Stealthy, Universal and Robust Audio Jailbreaks in Audio-Language Models Best-of-N Jailbreaking

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-09T18:05:52.279543Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 03886de2-ae14-407e-b3b6-41a4b5dedf0e · outbound

This paper cites and Liang, P.

"I am bad": Interpreting Stealthy, Universal and Robust Audio Jailbreaks in Audio-Language Models and Liang, P

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-09T18:05:52.283137Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 423c05fd-9c9d-41f1-b64f-be8c355461a8 · outbound

This paper cites M., Sun, J., and Chattopadhyay, S.

"I am bad": Interpreting Stealthy, Universal and Robust Audio Jailbreaks in Audio-Language Models M., Sun, J., and Chattopadhyay, S

Reference 23

Resolution: verified exact; arxiv_id_nonexistent, observed 2026-08-09T18:05:53.239601Z

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 041840ae-03d4-4b19-8736-402a9fcdfa6e · outbound

This paper cites Mixtral of Experts.

"I am bad": Interpreting Stealthy, Universal and Robust Audio Jailbreaks in Audio-Language Models Mixtral of Experts

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-09T18:05:52.289872Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 541756fa-360c-4b06-95e4-fd95f0abc85b · outbound

This paper cites AdvWave: Stealthy Adversarial Jailbreak Attack against Large Audio-Language Models.

"I am bad": Interpreting Stealthy, Universal and Robust Audio Jailbreaks in Audio-Language Models AdvWave: Stealthy Adversarial Jailbreak Attack against Large Audio-Language Models

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-09T18:05:52.293247Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 18360d4e-6246-40f1-919a-a41bef1a69d7 · outbound

This paper cites Towards Efficient Visual-Language Alignment of the Q-Former for Visual Reasoning Tasks.

"I am bad": Interpreting Stealthy, Universal and Robust Audio Jailbreaks in Audio-Language Models Towards Efficient Visual-Language Alignment of the Q-Former for Visual Reasoning Tasks

Reference 26

Resolution: verified exact; local_arxiv, observed 2026-08-09T18:05:53.055093Z

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 37755914-1b8c-4039-b0ec-023ebaf9f734 · outbound

This paper cites Voice biometrics fusion for enhanced security and speaker recognition: A comprehensive review.

"I am bad": Interpreting Stealthy, Universal and Robust Audio Jailbreaks in Audio-Language Models Voice biometrics fusion for enhanced security and speaker recognition: A comprehensive review

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T18:05:53.795167Z

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 e400b6bb-d269-4a65-91c0-f431c6157c37 · outbound

This paper cites Fooling end-to-end speaker verification with adversarial examples.

"I am bad": Interpreting Stealthy, Universal and Robust Audio Jailbreaks in Audio-Language Models Fooling end-to-end speaker verification with adversarial examples

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T18:05:53.783754Z

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 39bb094a-5346-4191-a8a1-d1488391ef6e · outbound

This paper cites AmpleGCG-Plus: A Strong Generative Model of Adversarial Suffixes to Jailbreak LLMs with Higher Success Rates in Fewer Attempts.

"I am bad": Interpreting Stealthy, Universal and Robust Audio Jailbreaks in Audio-Language Models AmpleGCG-Plus: A Strong Generative Model of Adversarial Suffixes to Jailbreak LLMs with Higher Success Rates in Fewer Attempts

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-09T18:05:52.306729Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6bf3f076-3aa4-400d-a15d-5c9e7dafadb9 · outbound

This paper cites Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking Multimodal Large Language Models.

"I am bad": Interpreting Stealthy, Universal and Robust Audio Jailbreaks in Audio-Language Models Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking Multimodal Large Language Models

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-09T18:05:52.310173Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4c967946-2540-43cf-81a1-b095aab1dff6 · outbound

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

"I am bad": Interpreting Stealthy, Universal and Robust Audio Jailbreaks in Audio-Language Models AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-09T18:05:52.313581Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4b1029c8-0ea8-4c86-9e42-13b5172ea68a · outbound

This paper cites Jailbreaking Prompt Attack: A Controllable Adversarial Attack against Diffusion Models.

"I am bad": Interpreting Stealthy, Universal and Robust Audio Jailbreaks in Audio-Language Models Jailbreaking Prompt Attack: A Controllable Adversarial Attack against Diffusion Models

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-09T18:05:52.317063Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f1ae30b2-45e4-4644-bc47-cf7de33041a1 · outbound

This paper cites User interaction patterns and breakdowns in conversing with llm-powered voice assistants.

"I am bad": Interpreting Stealthy, Universal and Robust Audio Jailbreaks in Audio-Language Models User interaction patterns and breakdowns in conversing with llm-powered voice assistants

Reference 33

Resolution: verified exact; arxiv_id_nonexistent, observed 2026-08-09T18:05:53.003628Z

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 5712b820-e111-4872-9133-134ee783c7dd · outbound

This paper cites Rule Based Rewards for Language Model Safety.

"I am bad": Interpreting Stealthy, Universal and Robust Audio Jailbreaks in Audio-Language Models Rule Based Rewards for Language Model Safety

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-09T18:05:52.323811Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c95fb8dc-f89a-4eae-96e7-5afcb3596340 · outbound

This paper cites GPT-4 Technical Report.

"I am bad": Interpreting Stealthy, Universal and Robust Audio Jailbreaks in Audio-Language Models GPT-4 Technical Report

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-09T18:05:52.327250Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b55288ce-0d88-46ee-a781-ce34e5ed02ee · outbound

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

"I am bad": Interpreting Stealthy, Universal and Robust Audio Jailbreaks in Audio-Language Models Training language models to follow instructions with human feedback

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-09T18:05:52.330474Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a053c25f-791b-4e62-bee6-b67f6605fa9b · outbound

This paper cites Red Teaming Language Models with Language Models.

"I am bad": Interpreting Stealthy, Universal and Robust Audio Jailbreaks in Audio-Language Models Red Teaming Language Models with Language Models

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-09T18:05:52.334192Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2dddea1c-6896-4130-9a1c-7cb95ca46e5e · outbound

This paper cites Visual Adversarial Examples Jailbreak Aligned Large Language Models.

"I am bad": Interpreting Stealthy, Universal and Robust Audio Jailbreaks in Audio-Language Models Visual Adversarial Examples Jailbreak Aligned Large Language Models

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-09T18:05:52.337707Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 14eb5793-877f-4d05-99f9-9a7cadc400e0 · outbound

This paper cites Robust Speech Recognition via Large-Scale Weak Supervision.

"I am bad": Interpreting Stealthy, Universal and Robust Audio Jailbreaks in Audio-Language Models Robust Speech Recognition via Large-Scale Weak Supervision

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-09T18:05:52.341242Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cbc995c3-5481-4a66-aca1-3eb0e873a171 · outbound

This paper cites Universal adversarial attacks on spoken language assessment systems.

"I am bad": Interpreting Stealthy, Universal and Robust Audio Jailbreaks in Audio-Language Models Universal adversarial attacks on spoken language assessment systems

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-09T18:05:52.344668Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ed9b5ece-75b5-4893-9bec-1d2ee61463ed · outbound

This paper cites Muting whisper: A universal acoustic adversarial attack on speech foundation models.

"I am bad": Interpreting Stealthy, Universal and Robust Audio Jailbreaks in Audio-Language Models Muting whisper: A universal acoustic adversarial attack on speech foundation models

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-09T18:05:52.348020Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3d95282a-3d47-4311-a85a-6d319bc863a3 · outbound

This paper cites Artificial Intelligence and the Problem of Control, pp.\ 19--24.

"I am bad": Interpreting Stealthy, Universal and Robust Audio Jailbreaks in Audio-Language Models Artificial Intelligence and the Problem of Control, pp.\ 19--24

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-09T18:05:52.351606Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 36d4c59f-dd61-4521-8fdc-2b4ebb0ac5d1 · outbound

This paper cites Failures to Find Transferable Image Jailbreaks Between Vision-Language Models.

"I am bad": Interpreting Stealthy, Universal and Robust Audio Jailbreaks in Audio-Language Models Failures to Find Transferable Image Jailbreaks Between Vision-Language Models

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-09T18:05:52.354966Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1534340e-a0aa-4139-9ec8-3c72299b783b · outbound

This paper cites Adversarial Attacks Against Automatic Speech Recognition Systems via Psychoacoustic Hiding.

"I am bad": Interpreting Stealthy, Universal and Robust Audio Jailbreaks in Audio-Language Models Adversarial Attacks Against Automatic Speech Recognition Systems via Psychoacoustic Hiding

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-09T18:05:52.358400Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 44c2689c-1bcf-45ec-b906-802d18747382 · outbound

This paper cites Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal Language Models.

"I am bad": Interpreting Stealthy, Universal and Robust Audio Jailbreaks in Audio-Language Models Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal Language Models

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-09T18:05:52.362053Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 536b9f55-816d-4bb6-9080-49c3f46acc1d · outbound

This paper cites "Do Anything Now": Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models.

"I am bad": Interpreting Stealthy, Universal and Robust Audio Jailbreaks in Audio-Language Models "Do Anything Now": Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-09T18:05:52.365731Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 094fc1c1-70b9-4523-aad5-925d36fe9675 · outbound

This paper cites Voice Jailbreak Attacks Against GPT-4o.

"I am bad": Interpreting Stealthy, Universal and Robust Audio Jailbreaks in Audio-Language Models Voice Jailbreak Attacks Against GPT-4o

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-09T18:05:52.369200Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 264d152f-056b-4332-aa16-87d27ed8cc7b · outbound

This paper cites Intriguing properties of neural networks.

"I am bad": Interpreting Stealthy, Universal and Robust Audio Jailbreaks in Audio-Language Models Intriguing properties of neural networks

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-09T18:05:52.372588Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 89928ea5-dc64-4c6f-afd7-993b1a80a66a · outbound

This paper cites SALMONN: Towards Generic Hearing Abilities for Large Language Models.

"I am bad": Interpreting Stealthy, Universal and Robust Audio Jailbreaks in Audio-Language Models SALMONN: Towards Generic Hearing Abilities for Large Language Models

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-09T18:05:52.376150Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7e6d5872-af8b-4fee-801a-888e189b8cc1 · outbound

This paper cites Universal Adversarial Triggers for Attacking and Analyzing NLP.

"I am bad": Interpreting Stealthy, Universal and Robust Audio Jailbreaks in Audio-Language Models Universal Adversarial Triggers for Attacking and Analyzing NLP

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-09T18:05:52.379750Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4e5b1b26-f85f-43b7-b49d-924f9d9b7389 · outbound

This paper cites Jailbroken: How Does LLM Safety Training Fail?.

"I am bad": Interpreting Stealthy, Universal and Robust Audio Jailbreaks in Audio-Language Models Jailbroken: How Does LLM Safety Training Fail?

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-09T18:05:52.383285Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 92e33961-2677-4e59-a605-8951d690c751 · outbound

This paper cites Finetuned Language Models Are Zero-Shot Learners.

"I am bad": Interpreting Stealthy, Universal and Robust Audio Jailbreaks in Audio-Language Models Finetuned Language Models Are Zero-Shot Learners

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-09T18:05:52.386625Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ec77abd3-e734-45ab-ac5a-7233f3539636 · outbound

This paper cites Ethical and social risks of harm from Language Models.

"I am bad": Interpreting Stealthy, Universal and Robust Audio Jailbreaks in Audio-Language Models Ethical and social risks of harm from Language Models

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-09T18:05:52.390059Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b2451446-b76f-4e00-a7bd-b54022459dc8 · outbound

This paper cites A Comprehensive Study of Jailbreak Attack versus Defense for Large Language Models.

"I am bad": Interpreting Stealthy, Universal and Robust Audio Jailbreaks in Audio-Language Models A Comprehensive Study of Jailbreak Attack versus Defense for Large Language Models

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-09T18:05:52.393696Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4f8975f0-ebc4-4b2b-a022-bdf6ac592f42 · outbound

This paper cites Audio Is the Achilles' Heel: Red Teaming Audio Large Multimodal Models.

"I am bad": Interpreting Stealthy, Universal and Robust Audio Jailbreaks in Audio-Language Models Audio Is the Achilles' Heel: Red Teaming Audio Large Multimodal Models

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-09T18:05:52.397110Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cbd27bd2-1236-41bb-afd4-924eb250e2aa · outbound

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

"I am bad": Interpreting Stealthy, Universal and Robust Audio Jailbreaks in Audio-Language Models Jailbreak Attacks and Defenses Against Large Language Models: A Survey

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-09T18:05:52.400556Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 80ed813d-ef3c-4083-beec-a5ac8fd8c19d · outbound

This paper cites Jailbreak Vision Language Models via Bi-Modal Adversarial Prompt.

"I am bad": Interpreting Stealthy, Universal and Robust Audio Jailbreaks in Audio-Language Models Jailbreak Vision Language Models via Bi-Modal Adversarial Prompt

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-09T18:05:52.403894Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eb2d21fa-7101-47ac-abfc-10b6c850db8f · outbound

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

"I am bad": Interpreting Stealthy, Universal and Robust Audio Jailbreaks in Audio-Language Models Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-09T18:05:52.407574Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5f9352e1-5df3-4545-b8e1-3c6765c05584 · outbound

This paper cites write newline.

"I am bad": Interpreting Stealthy, Universal and Robust Audio Jailbreaks in Audio-Language Models write newline

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-09T18:05:52.411107Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 640a865f-55a0-4642-866d-4bccf697773a · inbound

Universal Acoustic Adversarial Attacks for Flexible Control of Speech-LLMs cites this paper.

Universal Acoustic Adversarial Attacks for Flexible Control of Speech-LLMs "I am bad": Interpreting Stealthy, Universal and Robust Audio Jailbreaks in Audio-Language Models

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T15:42:19.934200Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 10f74bdd-f3ab-462e-abf1-6a4fb7fe297d · inbound

Towards Holistic Evaluation of Large Audio-Language Models: A Comprehensive Survey cites this paper.

Towards Holistic Evaluation of Large Audio-Language Models: A Comprehensive Survey "I am bad": Interpreting Stealthy, Universal and Robust Audio Jailbreaks in Audio-Language Models

Reference 3

Resolution: verified exact; arxiv_id, observed 2026-05-22T13:34:53.251853Z

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 120fea50-dc99-414f-bb87-b914e55d8ab7 · inbound

Investigating Vulnerabilities and Defenses Against Audio-Visual Attacks: A Comprehensive Survey Emphasizing Multimodal Models cites this paper.

Investigating Vulnerabilities and Defenses Against Audio-Visual Attacks: A Comprehensive Survey Emphasizing Multimodal Models "I am bad": Interpreting Stealthy, Universal and Robust Audio Jailbreaks in Audio-Language Models

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-07T04:08:42.306422Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 67fbab49-7064-461f-b6c2-c2d307b8a427 · inbound

On Optimizing Multimodal Jailbreaks for Spoken Language Models cites this paper.

On Optimizing Multimodal Jailbreaks for Spoken Language Models "I am bad": Interpreting Stealthy, Universal and Robust Audio Jailbreaks in Audio-Language Models

Reference 28

Resolution: unresolved; no resolver link, observed 2026-07-13T22:11:30.473038Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1194067e-34cb-480e-85ca-69dfcfece2f2 · inbound

Benign Fine-Tuning Breaks Safety Alignment in Audio LLMs cites this paper.

Benign Fine-Tuning Breaks Safety Alignment in Audio LLMs "I am bad": Interpreting Stealthy, Universal and Robust Audio Jailbreaks in Audio-Language Models

Reference 11

Resolution: metadata mismatch; arxiv_id, observed 2026-05-10T08:02:24.902416Z

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 8b3a05c7-410e-473e-8f02-9266fb140ce2 · inbound

A Survey of Large Audio Language Models: Generalization, Trustworthiness, and Outlook cites this paper.

A Survey of Large Audio Language Models: Generalization, Trustworthiness, and Outlook "I am bad": Interpreting Stealthy, Universal and Robust Audio Jailbreaks in Audio-Language Models

Reference 166

Resolution: verified exact; arxiv_id, observed 2026-05-21T07:39:48.672400Z

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 088c884f-afdc-4661-b5fa-1aa3c686eb4c · inbound

Audio Jailbreaks in Large Audio-Language Models: Taxonomy, Attack-Defense Analysis, and Cost-Aware Evaluation cites this paper.

Audio Jailbreaks in Large Audio-Language Models: Taxonomy, Attack-Defense Analysis, and Cost-Aware Evaluation "I am bad": Interpreting Stealthy, Universal and Robust Audio Jailbreaks in Audio-Language Models

Reference 5

Resolution: verified exact; arxiv_id, observed 2026-06-29T05:53:09.563735Z

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.