RedVox benchmark shows speech model safety and fairness vulnerabilities persist under non-adversarial conditions, worsen in non-English languages, and increase with spoken inputs.
Audio jailbreak: An open comprehensive benchmark for jailbreaking large audio-language models.arXiv preprint arXiv:2505.15406
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
dataset 1
citation-polarity summary
verdicts
UNVERDICTED 6roles
dataset 1polarities
use dataset 1representative citing papers
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 Qwen3-Omni-thinking while preserving general capabilities.
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.
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 unresolved attribution after separation.
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 that establishes a taxonomy of trustworthiness vulnerabilities and proposes a Defense-in-Depth roadmap for audio intelligence.
citing papers explorer
-
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 Qwen3-Omni-thinking while preserving general capabilities.
-
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 unresolved attribution after separation.
-
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.