Paper Citation Record · LEDGER

Audio Jailbreak: An Open Comprehensive Benchmark for Jailbreaking Large Audio-Language Models

As of 9 August 2026, this Paper Citation Record lists 57 of 57 outbound references and 9 inbound Pith citation observations for arXiv:2505.15406.

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

pith.paper-citation-record.v1
2505.15406 v1

Coverage vector

measured 57 of 57 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T15:23:04.010212Z

measured 66 of 66 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-08T06:32:00.761636+00:00

measured 9 of 9 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-06T20:01:29.101657Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-04T13:59:52.814698Z

Reference resolution

57 of 57 outbound references displayed

verified exact0
verified fuzzy13
unresolved44
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 7598b741-b824-4372-a081-aa55a75e3ada · outbound

This paper cites GPT-4 Technical Report.

Audio Jailbreak: An Open Comprehensive Benchmark for Jailbreaking Large Audio-Language Models GPT-4 Technical Report

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T15:23:00.520353Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 878317e2-89bc-4850-b524-fdd36535fa17 · outbound

This paper cites AudioLM: a Language Modeling Approach to Audio Generation.

Audio Jailbreak: An Open Comprehensive Benchmark for Jailbreaking Large Audio-Language Models AudioLM: a Language Modeling Approach to Audio Generation

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-07T15:23:00.586445Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 149ccc71-aab0-48e9-a4c3-b1047fe010c8 · outbound

This paper cites Benchlmm: Benchmarking cross-style visual capability of large multimodal models // European Conference on Computer Vision.

Audio Jailbreak: An Open Comprehensive Benchmark for Jailbreaking Large Audio-Language Models Benchlmm: Benchmarking cross-style visual capability of large multimodal models // European Conference on Computer Vision

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:23:06.813430Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 7cf5262a-a842-46bc-8240-26f4af2c54c2 · outbound

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

Audio Jailbreak: An Open Comprehensive Benchmark for Jailbreaking Large Audio-Language Models JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T15:23:00.686245Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b3046cd1-3de4-4f34-ada3-738dfcacd11d · outbound

This paper cites X-LLM: Bootstrapping Advanced Large Language Models by Treating Multi-Modalities as Foreign Languages.

Audio Jailbreak: An Open Comprehensive Benchmark for Jailbreaking Large Audio-Language Models X-LLM: Bootstrapping Advanced Large Language Models by Treating Multi-Modalities as Foreign Languages

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T15:23:00.732479Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 403523a6-1fd5-48cb-bf77-2241df91c196 · outbound

This paper cites Unveiling the power of language models in chemical research question answering // Communications Chemistry.

Audio Jailbreak: An Open Comprehensive Benchmark for Jailbreaking Large Audio-Language Models Unveiling the power of language models in chemical research question answering // Communications Chemistry

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:23:06.667549Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 7b87d514-3853-4a4a-8c59-a37e0dbd56f6 · outbound

This paper cites Qwen2-Audio Technical Report.

Audio Jailbreak: An Open Comprehensive Benchmark for Jailbreaking Large Audio-Language Models Qwen2-Audio Technical Report

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T15:23:00.899140Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 49e1752a-0443-4a6d-af31-1f3d106648b0 · outbound

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

Audio Jailbreak: An Open Comprehensive Benchmark for Jailbreaking Large Audio-Language Models Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T15:23:00.937688Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation be766e0b-d2a5-47d3-9a86-af69fb2285a3 · outbound

This paper cites Pengi: An audio language model for audio tasks // Advances in Neural Information Processing Systems.

Audio Jailbreak: An Open Comprehensive Benchmark for Jailbreaking Large Audio-Language Models Pengi: An audio language model for audio tasks // Advances in Neural Information Processing Systems

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:23:06.558009Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation cf5be773-4c3b-4785-95e6-2a4cf23981db · outbound

This paper cites The phase vocoder: A tutorial // Computer Music Journal.

Audio Jailbreak: An Open Comprehensive Benchmark for Jailbreaking Large Audio-Language Models The phase vocoder: A tutorial // Computer Music Journal

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:23:06.442005Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 28471991-f4b6-442c-ac2c-5bcd9650c886 · outbound

This paper cites When does contrastive learning preserve adversarial robustness from pretraining to finetuning? // Advances in neural information processing systems.

Audio Jailbreak: An Open Comprehensive Benchmark for Jailbreaking Large Audio-Language Models When does contrastive learning preserve adversarial robustness from pretraining to finetuning? // Advances in neural information processing systems

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:23:06.332081Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation dc9e1a5e-b5fa-4f82-8711-d91ee80fa622 · outbound

This paper cites LLaMA-Omni: Seamless Speech Interaction with Large Language Models.

Audio Jailbreak: An Open Comprehensive Benchmark for Jailbreaking Large Audio-Language Models LLaMA-Omni: Seamless Speech Interaction with Large Language Models

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T15:23:01.147173Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 68df4d41-e9eb-4ddd-bd5f-702551a6b126 · outbound

This paper cites Prompting large language models with speech recognition abilities // ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Audio Jailbreak: An Open Comprehensive Benchmark for Jailbreaking Large Audio-Language Models Prompting large language models with speech recognition abilities // ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:23:06.160143Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 92d5cb71-f2f4-49f0-abf1-5cafde38f643 · outbound

This paper cites A Tutorial on Bayesian Optimization.

Audio Jailbreak: An Open Comprehensive Benchmark for Jailbreaking Large Audio-Language Models A Tutorial on Bayesian Optimization

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T15:23:01.286272Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fc54a43b-0412-4f6c-a823-2e555c397ae1 · outbound

This paper cites an unresolved cited work.

Audio Jailbreak: An Open Comprehensive Benchmark for Jailbreaking Large Audio-Language Models Unresolved cited work

Reference 15

Resolution: unresolved; raw_fallback, observed 2026-08-07T15:23:06.030619Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation b83560eb-6c72-4f8f-bc06-60b13f5dd309 · outbound

This paper cites Shaping the Safety Boundaries: Understanding and Defending Against Jailbreaks in Large Language Models.

Audio Jailbreak: An Open Comprehensive Benchmark for Jailbreaking Large Audio-Language Models Shaping the Safety Boundaries: Understanding and Defending Against Jailbreaks in Large Language Models

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T15:23:01.399521Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7736233f-1a62-4215-91ab-9ca5f3ef4338 · outbound

This paper cites GAMA: A Large Audio-Language Model with Advanced Audio Understanding and Complex Reasoning Abilities.

Audio Jailbreak: An Open Comprehensive Benchmark for Jailbreaking Large Audio-Language Models GAMA: A Large Audio-Language Model with Advanced Audio Understanding and Complex Reasoning Abilities

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T15:23:01.440392Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1bcd468c-9691-4cef-ad2d-f78d419acf2b · outbound

This paper cites Listen, Think, and Understand.

Audio Jailbreak: An Open Comprehensive Benchmark for Jailbreaking Large Audio-Language Models Listen, Think, and Understand

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T15:23:01.487032Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7a5b2b43-06b5-4a4f-84c0-c711f0c589b4 · outbound

This paper cites MedINST: Meta Dataset of Biomedical Instructions.

Audio Jailbreak: An Open Comprehensive Benchmark for Jailbreaking Large Audio-Language Models MedINST: Meta Dataset of Biomedical Instructions

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T15:23:01.588714Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e9bebd05-8fbe-4d53-b74d-843f9e9c173f · outbound

This paper cites Distilling an End-to-End Voice Assistant Without Instruction Training Data.

Audio Jailbreak: An Open Comprehensive Benchmark for Jailbreaking Large Audio-Language Models Distilling an End-to-End Voice Assistant Without Instruction Training Data

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T15:23:01.636740Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d85f12f6-46a1-4b49-9b75-10a68e8d8692 · outbound

This paper cites On the Trustworthiness of Generative Foundation Models: Guideline, Assessment, and Perspective.

Audio Jailbreak: An Open Comprehensive Benchmark for Jailbreaking Large Audio-Language Models On the Trustworthiness of Generative Foundation Models: Guideline, Assessment, and Perspective

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T15:23:01.681691Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation deab6ffb-3312-4d70-9c79-307d167e06cc · outbound

This paper cites Breaking Focus: Contextual Distraction Curse in Large Language Models // arXiv preprint arXiv:2502.01609.

Audio Jailbreak: An Open Comprehensive Benchmark for Jailbreaking Large Audio-Language Models Breaking Focus: Contextual Distraction Curse in Large Language Models // arXiv preprint arXiv:2502.01609

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T15:23:01.726140Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2eb2895a-8b70-4ba9-a4b1-72f283573b16 · outbound

This paper cites Best-of-N Jailbreaking.

Audio Jailbreak: An Open Comprehensive Benchmark for Jailbreaking Large Audio-Language Models Best-of-N Jailbreaking

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T15:23:01.792126Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 597f482d-0e88-42a5-94ce-f8a28a0ec0f2 · outbound

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

Audio Jailbreak: An Open Comprehensive Benchmark for Jailbreaking Large Audio-Language Models AdvWave: Stealthy Adversarial Jailbreak Attack against Large Audio-Language Models

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T15:23:01.879152Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0de53495-e92f-43d3-a20c-922b0e3ce738 · outbound

This paper cites On generative spoken language modeling from raw audio // Transactions of the Association for Computational Linguistics.

Audio Jailbreak: An Open Comprehensive Benchmark for Jailbreaking Large Audio-Language Models On generative spoken language modeling from raw audio // Transactions of the Association for Computational Linguistics

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:23:05.860628Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 364709af-c496-489e-a38a-8bb2476330c3 · outbound

This paper cites Appagent v2: Advanced agent for flexible mobile interactions // arXiv preprint arXiv:2408.11824.

Audio Jailbreak: An Open Comprehensive Benchmark for Jailbreaking Large Audio-Language Models Appagent v2: Advanced agent for flexible mobile interactions // arXiv preprint arXiv:2408.11824

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T15:23:01.968676Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 081e9339-f6f7-42ea-9357-433d651db1c7 · outbound

This paper cites The Unlocking Spell on Base LLMs: Rethinking Alignment via In-Context Learning.

Audio Jailbreak: An Open Comprehensive Benchmark for Jailbreaking Large Audio-Language Models The Unlocking Spell on Base LLMs: Rethinking Alignment via In-Context Learning

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-07T15:23:02.007476Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e80b5488-f604-4a6e-9bf8-64e24c0699db · outbound

This paper cites DeepSeek-V3 Technical Report.

Audio Jailbreak: An Open Comprehensive Benchmark for Jailbreaking Large Audio-Language Models DeepSeek-V3 Technical Report

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T15:23:02.108648Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 744829b7-db84-4717-ae27-c546e16a6251 · outbound

This paper cites The Stepwise Deception: Simulating the Evolution from True News to Fake News with LLM Agents.

Audio Jailbreak: An Open Comprehensive Benchmark for Jailbreaking Large Audio-Language Models The Stepwise Deception: Simulating the Evolution from True News to Fake News with LLM Agents

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T15:23:02.176423Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9b5bae6b-6cc0-442f-9763-014445911a9e · outbound

This paper cites Semi-Supervised Audio Classification with Consistency-Based Regularization.

Audio Jailbreak: An Open Comprehensive Benchmark for Jailbreaking Large Audio-Language Models Semi-Supervised Audio Classification with Consistency-Based Regularization

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:23:05.711665Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation ca56d13a-6ae1-47f2-8bb2-cbfae82600fe · outbound

This paper cites Spoken Question Answering and Speech Continuation Using Spectrogram-Powered LLM.

Audio Jailbreak: An Open Comprehensive Benchmark for Jailbreaking Large Audio-Language Models Spoken Question Answering and Speech Continuation Using Spectrogram-Powered LLM

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-07T15:23:02.306051Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9bf90d67-6483-4171-9319-5c844864419e · outbound

This paper cites GPT-4o System Card.

Audio Jailbreak: An Open Comprehensive Benchmark for Jailbreaking Large Audio-Language Models GPT-4o System Card

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:23:05.493281Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation c6f8883c-a238-4374-a738-f4a48ca2e6ee · outbound

This paper cites Robust speech recognition via large-scale weak supervision // International conference on machine learning.

Audio Jailbreak: An Open Comprehensive Benchmark for Jailbreaking Large Audio-Language Models Robust speech recognition via large-scale weak supervision // International conference on machine learning

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:23:05.293333Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation b15cb1dd-8681-4a9b-9144-e7b62a26388e · outbound

This paper cites Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context.

Audio Jailbreak: An Open Comprehensive Benchmark for Jailbreaking Large Audio-Language Models Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-07T15:23:02.488545Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 685266cb-e724-4002-aa77-91c78b6438ee · outbound

This paper cites Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks.

Audio Jailbreak: An Open Comprehensive Benchmark for Jailbreaking Large Audio-Language Models Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-07T15:23:02.574675Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 07f45772-dcd5-4b4f-b063-9b2910745024 · outbound

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

Audio Jailbreak: An Open Comprehensive Benchmark for Jailbreaking Large Audio-Language Models "Do Anything Now": Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-07T15:23:02.652356Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 70fada26-c9f2-497b-be8e-ad7fecc34ae4 · outbound

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

Audio Jailbreak: An Open Comprehensive Benchmark for Jailbreaking Large Audio-Language Models Voice Jailbreak Attacks Against GPT-4o

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-07T15:23:02.718736Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2bbd188d-7258-4011-9421-be4bef6806dd · outbound

This paper cites MMAC-Copilot: Multi-modal Agent Collaboration Operating Copilot.

Audio Jailbreak: An Open Comprehensive Benchmark for Jailbreaking Large Audio-Language Models MMAC-Copilot: Multi-modal Agent Collaboration Operating Copilot

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-07T15:23:02.806149Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aa19044d-0fb0-4ca3-b729-09d96db6621a · outbound

This paper cites Hazards in Daily Life? Enabling Robots to Proactively Detect and Resolve Anomalies.

Audio Jailbreak: An Open Comprehensive Benchmark for Jailbreaking Large Audio-Language Models Hazards in Daily Life? Enabling Robots to Proactively Detect and Resolve Anomalies

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-07T15:23:02.864812Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 72687450-45bb-4fad-819c-71493aae0c64 · outbound

This paper cites Injecting Domain-Specific Knowledge into Large Language Models: A Comprehensive Survey.

Audio Jailbreak: An Open Comprehensive Benchmark for Jailbreaking Large Audio-Language Models Injecting Domain-Specific Knowledge into Large Language Models: A Comprehensive Survey

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-07T15:23:02.924153Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a940e22c-b5cf-4a0c-8454-71bab046d0e9 · outbound

This paper cites Geolocation with Real Human Gameplay Data: A Large-Scale Dataset and Human-Like Reasoning Framework // arXiv preprint arXiv:2502.13759.

Audio Jailbreak: An Open Comprehensive Benchmark for Jailbreaking Large Audio-Language Models Geolocation with Real Human Gameplay Data: A Large-Scale Dataset and Human-Like Reasoning Framework // arXiv preprint arXiv:2502.13759

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-07T15:23:03.023360Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c7aa87d2-76f0-434a-bbbf-bd1f5efc4938 · outbound

This paper cites FunAudioLLM: Voice Understanding and Generation Foundation Models for Natural Interaction Between Humans and LLMs.

Audio Jailbreak: An Open Comprehensive Benchmark for Jailbreaking Large Audio-Language Models FunAudioLLM: Voice Understanding and Generation Foundation Models for Natural Interaction Between Humans and LLMs

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-07T15:23:03.080825Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e79854be-f6b5-4ec1-b729-de796a11c984 · outbound

This paper cites Uncertainty-aware audiovisual activity recognition using deep bayesian variational inference // Proceedings of the IEEE/CVF international conference on computer vision.

Audio Jailbreak: An Open Comprehensive Benchmark for Jailbreaking Large Audio-Language Models Uncertainty-aware audiovisual activity recognition using deep bayesian variational inference // Proceedings of the IEEE/CVF international conference on computer vision

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:23:05.176210Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 9ee6abce-ebcb-4242-83c9-4d258b3341c5 · outbound

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

Audio Jailbreak: An Open Comprehensive Benchmark for Jailbreaking Large Audio-Language Models SALMONN: Towards Generic Hearing Abilities for Large Language Models

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-07T15:23:03.204970Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3d668558-ce22-46b3-8aa0-da12d6dc8533 · outbound

This paper cites Word Form Matters: LLMs' Semantic Reconstruction under Typoglycemia.

Audio Jailbreak: An Open Comprehensive Benchmark for Jailbreaking Large Audio-Language Models Word Form Matters: LLMs' Semantic Reconstruction under Typoglycemia

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-07T15:23:03.261377Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4f65ed92-a07d-4eba-b903-d475e502c3ad · outbound

This paper cites VioLA: Unified Codec Language Models for Speech Recognition, Synthesis, and Translation.

Audio Jailbreak: An Open Comprehensive Benchmark for Jailbreaking Large Audio-Language Models VioLA: Unified Codec Language Models for Speech Recognition, Synthesis, and Translation

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-07T15:23:03.314763Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1929dd54-4ffb-41f3-8da3-c6abc5681a79 · outbound

This paper cites an unresolved cited work.

Audio Jailbreak: An Open Comprehensive Benchmark for Jailbreaking Large Audio-Language Models Unresolved cited work

Reference 47

Resolution: unresolved; raw_fallback, observed 2026-08-07T15:23:05.034694Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation eb6fa4e2-26a0-45e8-97e8-974bf38c77fb · outbound

This paper cites Tree-Structured Parzen Estimator: Understanding Its Algorithm Components and Their Roles for Better Empirical Performance.

Audio Jailbreak: An Open Comprehensive Benchmark for Jailbreaking Large Audio-Language Models Tree-Structured Parzen Estimator: Understanding Its Algorithm Components and Their Roles for Better Empirical Performance

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-07T15:23:03.437115Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cab37f51-1b86-434f-9f0c-d6261bc06c5d · outbound

This paper cites On decoder-only architecture for speech-to-text and large language model integration // 2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU).

Audio Jailbreak: An Open Comprehensive Benchmark for Jailbreaking Large Audio-Language Models On decoder-only architecture for speech-to-text and large language model integration // 2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:23:04.914786Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 489727a3-afcd-4908-9d9c-f9f8f5e0b8df · outbound

This paper cites NExT-GPT: Any-to-Any Multimodal LLM.

Audio Jailbreak: An Open Comprehensive Benchmark for Jailbreaking Large Audio-Language Models NExT-GPT: Any-to-Any Multimodal LLM

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-07T15:23:03.563984Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7715cdcd-02e7-4453-8ff8-6f024434de7c · outbound

This paper cites Tune In, Act Up: Exploring the Impact of Audio Modality-Specific Edits on Large Audio Language Models in Jailbreak // arXiv preprint arXiv:2501.13772.

Audio Jailbreak: An Open Comprehensive Benchmark for Jailbreaking Large Audio-Language Models Tune In, Act Up: Exploring the Impact of Audio Modality-Specific Edits on Large Audio Language Models in Jailbreak // arXiv preprint arXiv:2501.13772

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-07T15:23:03.611324Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5b6bc949-bb67-4e16-ae07-5c37c9392648 · outbound

This paper cites MedTrinity-25M: A Large-scale Multimodal Dataset with Multigranular Annotations for Medicine.

Audio Jailbreak: An Open Comprehensive Benchmark for Jailbreaking Large Audio-Language Models MedTrinity-25M: A Large-scale Multimodal Dataset with Multigranular Annotations for Medicine

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:23:04.785627Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation ac45c727-7552-4005-bf59-aa94ff80e20f · outbound

This paper cites Mini-Omni: Language Models Can Hear, Talk While Thinking in Streaming.

Audio Jailbreak: An Open Comprehensive Benchmark for Jailbreaking Large Audio-Language Models Mini-Omni: Language Models Can Hear, Talk While Thinking in Streaming

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-07T15:23:03.760260Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2c8a081b-e87f-4448-8d6b-83e182e5bd67 · outbound

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

Audio Jailbreak: An Open Comprehensive Benchmark for Jailbreaking Large Audio-Language Models Audio Is the Achilles' Heel: Red Teaming Audio Large Multimodal Models

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-07T15:23:03.832495Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bf0da2a0-4557-45b0-87f0-095555012f49 · outbound

This paper cites Unveiling the Safety of GPT-4o: An Empirical Study using Jailbreak Attacks.

Audio Jailbreak: An Open Comprehensive Benchmark for Jailbreaking Large Audio-Language Models Unveiling the Safety of GPT-4o: An Empirical Study using Jailbreak Attacks

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-07T15:23:03.879687Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3779bbc0-9a67-4738-bbb6-19f27823bcf2 · outbound

This paper cites SpeechGPT: Empowering Large Language Models with Intrinsic Cross-Modal Conversational Abilities.

Audio Jailbreak: An Open Comprehensive Benchmark for Jailbreaking Large Audio-Language Models SpeechGPT: Empowering Large Language Models with Intrinsic Cross-Modal Conversational Abilities

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-07T15:23:03.939492Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b46e04f3-5895-4420-9e00-c87e2cbd00e0 · outbound

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

Audio Jailbreak: An Open Comprehensive Benchmark for Jailbreaking Large Audio-Language Models Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-07T15:23:04.010212Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation b787ab99-1793-48c0-a3fd-44975853b2ca · inbound

Phonetic Perturbations Reveal Tokenizer-Rooted Safety Gaps in LLMs cites this paper.

Phonetic Perturbations Reveal Tokenizer-Rooted Safety Gaps in LLMs Audio Jailbreak: An Open Comprehensive Benchmark for Jailbreaking Large Audio-Language Models

Reference 20

Resolution: verified exact; arxiv_id, observed 2026-05-22T14:41:41.447184Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 3c24cbcf-69cf-4df7-b40a-5d88ccaa7dba · inbound

PresentAgent: Multimodal Agent for Presentation Video Generation cites this paper.

PresentAgent: Multimodal Agent for Presentation Video Generation Audio Jailbreak: An Open Comprehensive Benchmark for Jailbreaking Large Audio-Language Models

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-06T20:01:29.101657Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 84f927ca-2991-4e01-859c-5bddd2c27880 · inbound

ChronosAudio: A Comprehensive Long-Audio Benchmark for Evaluating Audio-Large Language Models cites this paper.

ChronosAudio: A Comprehensive Long-Audio Benchmark for Evaluating Audio-Large Language Models Audio Jailbreak: An Open Comprehensive Benchmark for Jailbreaking Large Audio-Language Models

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-03T11:56:08.058417Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e1e3656-2c13-429e-a0a0-dbb558ce4d48 · inbound

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

On Optimizing Multimodal Jailbreaks for Spoken Language Models Audio Jailbreak: An Open Comprehensive Benchmark for Jailbreaking Large Audio-Language Models

Reference 31

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 331b3224-b194-4b0d-9d77-e0a96c6b3ba4 · inbound

Can Large Audio Language Models Ignore Multilingual Distractors? An Evaluation of Their Selective Auditory Attention Capabilities cites this paper.

Can Large Audio Language Models Ignore Multilingual Distractors? An Evaluation of Their Selective Auditory Attention Capabilities Audio Jailbreak: An Open Comprehensive Benchmark for Jailbreaking Large Audio-Language Models

Reference 16

Resolution: verified exact; arxiv_id, observed 2026-05-19T23:17:57.425254Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 637a9c5e-df3b-4e98-a5ad-415e0865c6ba · inbound

Acoustic Interference: A New Paradigm Weaponizing Acoustic Latent Semantic for Universal Jailbreak against Large Audio Language Models cites this paper.

Acoustic Interference: A New Paradigm Weaponizing Acoustic Latent Semantic for Universal Jailbreak against Large Audio Language Models Audio Jailbreak: An Open Comprehensive Benchmark for Jailbreaking Large Audio-Language Models

Reference 38

Resolution: verified exact; arxiv_id, observed 2026-05-20T09:53:15.969331Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 52be56bc-4ee2-46cd-b658-70a0c890bf95 · 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 Audio Jailbreak: An Open Comprehensive Benchmark for Jailbreaking Large Audio-Language Models

Reference 169

Resolution: verified exact; arxiv_id, observed 2026-05-21T07:39:48.840914Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation dc537d9d-b741-4ec1-9695-aaa12fbc4006 · inbound

ParaBridge: Bridging Paralinguistic Perception and Dialogue Behavior in Speech Language Models cites this paper.

ParaBridge: Bridging Paralinguistic Perception and Dialogue Behavior in Speech Language Models Audio Jailbreak: An Open Comprehensive Benchmark for Jailbreaking Large Audio-Language Models

Reference 7

Resolution: metadata mismatch; arxiv_id, observed 2026-07-03T05:07:39.459073Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 13948d62-8a8e-4d9a-a12d-b2b46744b58b · inbound

RedVox: Safety and Fairness Gaps in Speech Models Across Languages cites this paper.

RedVox: Safety and Fairness Gaps in Speech Models Across Languages Audio Jailbreak: An Open Comprehensive Benchmark for Jailbreaking Large Audio-Language Models

Reference 154

Resolution: verified exact; arxiv_id, observed 2026-07-04T13:59:52.816236Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.