REVIEW 8 cited by
Audio Jailbreak: An Open Comprehensive Benchmark for Jailbreaking Large Audio-Language Models
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Audio Jailbreak: An Open Comprehensive Benchmark for Jailbreaking Large Audio-Language Models
read the original abstract
The rise of Large Audio Language Models (LAMs) brings both potential and risks, as their audio outputs may contain harmful or unethical content. However, current research lacks a systematic, quantitative evaluation of LAM safety especially against jailbreak attacks, which are challenging due to the temporal and semantic nature of speech. To bridge this gap, we introduce AJailBench, the first benchmark specifically designed to evaluate jailbreak vulnerabilities in LAMs. We begin by constructing AJailBench-Base, a dataset of 1,495 adversarial audio prompts spanning 10 policy-violating categories, converted from textual jailbreak attacks using realistic text to speech synthesis. Using this dataset, we evaluate several state-of-the-art LAMs and reveal that none exhibit consistent robustness across attacks. To further strengthen jailbreak testing and simulate more realistic attack conditions, we propose a method to generate dynamic adversarial variants. Our Audio Perturbation Toolkit (APT) applies targeted distortions across time, frequency, and amplitude domains. To preserve the original jailbreak intent, we enforce a semantic consistency constraint and employ Bayesian optimization to efficiently search for perturbations that are both subtle and highly effective. This results in AJailBench-APT, an extended dataset of optimized adversarial audio samples. Our findings demonstrate that even small, semantically preserved perturbations can significantly reduce the safety performance of leading LAMs, underscoring the need for more robust and semantically aware defense mechanisms.
Forward citations
Cited by 8 Pith papers
-
RedVox: Safety and Fairness Gaps in Speech Models Across Languages
RedVox benchmark shows speech model safety and fairness vulnerabilities persist under non-adversarial conditions, worsen in non-English languages, and increase with spoken inputs.
-
ParaBridge: Bridging Paralinguistic Perception and Dialogue Behavior in Speech Language Models
ParaBridge applies on-policy self-distillation with a scaffold as privileged view to convert brittle inference-time paralinguistic guidance into stable model behavior, raising VoxSafeBench SAR from 14.6% to 40.3% on Q...
-
Acoustic Interference: A New Paradigm Weaponizing Acoustic Latent Semantic for Universal Jailbreak against Large Audio Language Models
AIA generates universal interference audio infused with Acoustic Latent Semantics to bypass LALM safety alignment, achieving SOTA attack success rates on 10 models across five datasets.
-
Can Large Audio Language Models Ignore Multilingual Distractors? An Evaluation of Their Selective Auditory Attention Capabilities
Introduces the MUSA benchmark and evaluates LALMs showing that strong single-speaker performance fails to ensure robust selective attention under multilingual interference, with errors from source confusion and unreso...
-
On Optimizing Multimodal Jailbreaks for Spoken Language Models
JAMA jointly optimizes GCG text suffixes and PGD audio perturbations, lifting SLM jailbreak rates 1.5–10× over unimodal attacks; a sequential approximation recovers most of the gain at 4–6× lower cost.
-
Phonetic Perturbations Reveal Tokenizer-Rooted Safety Gaps in LLMs
Phonetic perturbations fragment safety-critical tokens in LLMs, suppressing attribution scores while preserving input understanding and causing safety mechanisms to fail despite good comprehension.
-
A Survey of Large Audio Language Models: Generalization, Trustworthiness, and Outlook
A survey of Large Audio Language Models that establishes a taxonomy of trustworthiness vulnerabilities and proposes a Defense-in-Depth roadmap for audio intelligence.
-
ChronosAudio: A Comprehensive Long-Audio Benchmark for Evaluating Audio-Large Language Models
A long-audio benchmark claims severe performance collapse in 16 audio LLMs, but unspecified metric weights and internal inconsistencies make the headline numbers uninterpretable.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.