Paper Citation Record · LEDGER

Audio Jailbreak Attacks: Exposing Vulnerabilities in SpeechGPT in a White-Box Framework

As of 8 August 2026, this Paper Citation Record lists 35 of 35 outbound references and 0 inbound Pith citation observations for arXiv:2505.18864.

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

pith.paper-citation-record.v1
2505.18864 v1

Coverage vector

measured 35 of 35 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T14:27:07.201702Z

measured 35 of 35 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 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

35 of 35 outbound references displayed

verified exact0
verified fuzzy8
unresolved27
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 9783f24b-c7e0-464c-a996-405b245d9c81 · outbound

This paper cites Visual instruction tuning,.

Audio Jailbreak Attacks: Exposing Vulnerabilities in SpeechGPT in a White-Box Framework Visual instruction tuning,

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T14:27:05.132678Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1fc38698-cb47-41b6-af77-d56762fd6d30 · outbound

This paper cites GPT-4 Technical Report.

Audio Jailbreak Attacks: Exposing Vulnerabilities in SpeechGPT in a White-Box Framework GPT-4 Technical Report

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-07T14:27:05.196595Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e81487cf-ddf4-43f5-ad6d-e85a6d6ba353 · outbound

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

Audio Jailbreak Attacks: Exposing Vulnerabilities in SpeechGPT in a White-Box Framework SpeechGPT: Empowering Large Language Models with Intrinsic Cross-Modal Conversational Abilities

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T14:27:05.265383Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eb7a9dfb-db57-4172-ab6b-1cc63bff6664 · outbound

This paper cites Next-gpt: Any-to-any multimodal llm,.

Audio Jailbreak Attacks: Exposing Vulnerabilities in SpeechGPT in a White-Box Framework Next-gpt: Any-to-any multimodal llm,

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T14:27:05.360972Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bf40bfaa-f3ff-4554-9c86-b7bd836d17cb · outbound

This paper cites GPT-4o System Card.

Audio Jailbreak Attacks: Exposing Vulnerabilities in SpeechGPT in a White-Box Framework GPT-4o System Card

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T14:27:05.421186Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8ae256d3-57df-453d-91ee-bf054a762f04 · outbound

This paper cites Introducing copilot+ pcs,.

Audio Jailbreak Attacks: Exposing Vulnerabilities in SpeechGPT in a White-Box Framework Introducing copilot+ pcs,

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:27:09.002097Z

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 a9f1d635-76e6-4968-95bb-824d7747ff71 · outbound

This paper cites People are suddenly flocking to chatgpt plus on mobile – here’s why,.

Audio Jailbreak Attacks: Exposing Vulnerabilities in SpeechGPT in a White-Box Framework People are suddenly flocking to chatgpt plus on mobile – here’s why,

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:27:08.823172Z

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 3ba6d420-11dd-49d2-886c-bb90d9cf8262 · outbound

This paper cites Apple is finalizing a deal with openai to put chatgpt on the iphone, while talks with google to use gemini are ongoing,.

Audio Jailbreak Attacks: Exposing Vulnerabilities in SpeechGPT in a White-Box Framework Apple is finalizing a deal with openai to put chatgpt on the iphone, while talks with google to use gemini are ongoing,

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:27:08.653643Z

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 410cd221-4ffe-405a-bedf-a2119c9870f6 · outbound

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

Audio Jailbreak Attacks: Exposing Vulnerabilities in SpeechGPT in a White-Box Framework Voice Jailbreak Attacks Against GPT-4o

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T14:27:05.448953Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ff308d94-1d19-4bd4-9ccb-5d87ccfa5b57 · outbound

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

Audio Jailbreak Attacks: Exposing Vulnerabilities in SpeechGPT in a White-Box Framework AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T14:27:05.454954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 874ccb10-04bf-45d1-8d33-79a4164ba43f · outbound

This paper cites " do anything now.

Audio Jailbreak Attacks: Exposing Vulnerabilities in SpeechGPT in a White-Box Framework " do anything now

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:27:08.474985Z

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 78cda8c7-098c-4013-93ad-318f79697e19 · outbound

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

Audio Jailbreak Attacks: Exposing Vulnerabilities in SpeechGPT in a White-Box Framework Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T14:27:05.502184Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aac3bf77-b9b6-49fa-9ce9-9d6e4c5988cb · outbound

This paper cites Gpt-4v system card,.

Audio Jailbreak Attacks: Exposing Vulnerabilities in SpeechGPT in a White-Box Framework Gpt-4v system card,

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:27:08.313749Z

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 704992cc-917f-4293-987e-29d345098244 · outbound

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

Audio Jailbreak Attacks: Exposing Vulnerabilities in SpeechGPT in a White-Box Framework JailbreakRadar: Comprehensive Assessment of Jailbreak Attacks Against LLMs

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T14:27:05.591822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c2599b70-d583-44e8-89c5-536f57c6585f · outbound

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

Audio Jailbreak Attacks: Exposing Vulnerabilities in SpeechGPT in a White-Box Framework Catastrophic Jailbreak of Open-source LLMs via Exploiting Generation

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T14:27:05.636865Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0a8124b6-20c0-41e0-a7c7-ed3b7ee9bce7 · outbound

This paper cites FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts.

Audio Jailbreak Attacks: Exposing Vulnerabilities in SpeechGPT in a White-Box Framework FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T14:27:05.699522Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f0a5b696-8e6d-41ff-a1ee-460b73b5c2e8 · outbound

This paper cites Multi-step Jailbreaking Privacy Attacks on ChatGPT.

Audio Jailbreak Attacks: Exposing Vulnerabilities in SpeechGPT in a White-Box Framework Multi-step Jailbreaking Privacy Attacks on ChatGPT

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T14:27:05.763058Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8ebe53d3-3459-4b01-9a48-555e3fffaf5d · outbound

This paper cites HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal.

Audio Jailbreak Attacks: Exposing Vulnerabilities in SpeechGPT in a White-Box Framework HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T14:27:05.797087Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6c181256-d750-46cf-972b-abfc24242958 · outbound

This paper cites A StrongREJECT for Empty Jailbreaks.

Audio Jailbreak Attacks: Exposing Vulnerabilities in SpeechGPT in a White-Box Framework A StrongREJECT for Empty Jailbreaks

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T14:27:05.836755Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7fb17c4f-ce07-4216-a432-6cc16cd5fb34 · outbound

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

Audio Jailbreak Attacks: Exposing Vulnerabilities in SpeechGPT in a White-Box Framework Jailbroken: How does llm safety training fail?

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T14:27:05.882294Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation be5d8f43-0a84-4ea0-85cc-d1bfdc3b8e6c · outbound

This paper cites Defending chatgpt against jailbreak attack via self-reminders,.

Audio Jailbreak Attacks: Exposing Vulnerabilities in SpeechGPT in a White-Box Framework Defending chatgpt against jailbreak attack via self-reminders,

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T14:27:05.959381Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7a45aba8-a5a4-4d25-8c3a-d1ce07d05868 · outbound

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

Audio Jailbreak Attacks: Exposing Vulnerabilities in SpeechGPT in a White-Box Framework GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T14:27:05.964702Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0fd5edc6-90e2-417c-a5d7-48dc562f7d80 · outbound

This paper cites Multilingual Jailbreak Challenges in Large Language Models.

Audio Jailbreak Attacks: Exposing Vulnerabilities in SpeechGPT in a White-Box Framework Multilingual Jailbreak Challenges in Large Language Models

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T14:27:06.003650Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 87021e4c-06e4-467e-89ff-3457213ba352 · outbound

This paper cites Low-Resource Languages Jailbreak GPT-4.

Audio Jailbreak Attacks: Exposing Vulnerabilities in SpeechGPT in a White-Box Framework Low-Resource Languages Jailbreak GPT-4

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-07T14:27:06.090288Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f588b785-fd02-44b0-aac1-b43d8a6d78be · outbound

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

Audio Jailbreak Attacks: Exposing Vulnerabilities in SpeechGPT in a White-Box Framework Jailbreaking Black Box Large Language Models in Twenty Queries

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T14:27:06.152780Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c9f550d4-bac2-4c9a-8f7e-a883cc451fa8 · outbound

This paper cites Tree of attacks: Jailbreaking black-box llms automatically,.

Audio Jailbreak Attacks: Exposing Vulnerabilities in SpeechGPT in a White-Box Framework Tree of attacks: Jailbreaking black-box llms automatically,

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:27:08.093291Z

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 2a70d9d9-063a-4599-956a-316db09dbcd7 · outbound

This paper cites SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks.

Audio Jailbreak Attacks: Exposing Vulnerabilities in SpeechGPT in a White-Box Framework SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T14:27:06.363295Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4e1a0703-3e20-4acb-b942-224d849ed9cf · outbound

This paper cites Vlattack: Multimodal adversarial attacks on vision-language tasks via pre-trained models,.

Audio Jailbreak Attacks: Exposing Vulnerabilities in SpeechGPT in a White-Box Framework Vlattack: Multimodal adversarial attacks on vision-language tasks via pre-trained models,

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T14:27:06.468716Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 647c464e-d2df-49d8-91f6-42febe3974d7 · outbound

This paper cites Probing the Robustness of Vision-Language Pretrained Models: A Multimodal Adversarial Attack Approach.

Audio Jailbreak Attacks: Exposing Vulnerabilities in SpeechGPT in a White-Box Framework Probing the Robustness of Vision-Language Pretrained Models: A Multimodal Adversarial Attack Approach

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-07T14:27:06.572513Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ddb7fb76-9a77-4eaa-8de0-e4fc68336ab8 · outbound

This paper cites Image-based multimodal models as intruders: Trans- ferable multimodal attacks on video-based mllms,.

Audio Jailbreak Attacks: Exposing Vulnerabilities in SpeechGPT in a White-Box Framework Image-based multimodal models as intruders: Trans- ferable multimodal attacks on video-based mllms,

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-07T14:27:06.666118Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bf78ab1e-36eb-473a-8bc8-9d1f8f7f2ba8 · outbound

This paper cites Hubert: Self-supervised speech representation learning by masked prediction of hidden units,.

Audio Jailbreak Attacks: Exposing Vulnerabilities in SpeechGPT in a White-Box Framework Hubert: Self-supervised speech representation learning by masked prediction of hidden units,

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-07T14:27:06.804910Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3f6c8191-14d5-45c4-8fe3-680a2cd6ff6b · outbound

This paper cites Speech Resynthesis from Discrete Disentangled Self-Supervised Representations.

Audio Jailbreak Attacks: Exposing Vulnerabilities in SpeechGPT in a White-Box Framework Speech Resynthesis from Discrete Disentangled Self-Supervised Representations

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-07T14:27:06.919635Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fbc169dc-dcb2-48f8-9ee6-c98134c5b063 · outbound

This paper cites Usage policies,.

Audio Jailbreak Attacks: Exposing Vulnerabilities in SpeechGPT in a White-Box Framework Usage policies,

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:27:07.794666Z

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 acce009c-0393-49ea-a7a9-d118aa8da34c · outbound

This paper cites NISQA: A Deep CNN-Self-Attention Model for Multidimensional Speech Quality Prediction with Crowdsourced Datasets.

Audio Jailbreak Attacks: Exposing Vulnerabilities in SpeechGPT in a White-Box Framework NISQA: A Deep CNN-Self-Attention Model for Multidimensional Speech Quality Prediction with Crowdsourced Datasets

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-07T14:27:07.110867Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 554ab645-b265-4783-80e9-c56a86c7836a · outbound

This paper cites Openai text-to-speech (tts) models,.

Audio Jailbreak Attacks: Exposing Vulnerabilities in SpeechGPT in a White-Box Framework Openai text-to-speech (tts) models,

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:27:07.597896Z

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.

Pith citing papers

No inbound Pith citation observations are available.