- Rating
- 2
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper investigates denial-of-service (DoS) attacks against end-to-end speech language models by optimizing acoustic perturbations to induce prolonged autoregressive generation while preserving the original input length. The proposed white-box attack uses projected gradient descent with a composite objective comprising weighted EOS loss, top-k logit loss, length loss, and semantic alignment loss. Voice activity detection (VAD) further restricts perturbations to voiced regions. Experiments on three open-source audio language models demonstrate the effectiveness of the proposed attack.
Critical strengths
- The research problem is meaningful. Studying DoS attacks on End-to-End speech language models contributes to highlighting practical vulnerabilities in ALLM systems.
- The methodology is straightforward and easy to understand. The attack constructs adversarial perturbations through a multi-objective loss designed to prolong generation and enable DoS attacks on ALLMs.
- The paper is generally well-organized and easy to read.
Critical weaknesses
- The novelty of the method is limited. The authors simply adapt audio adversarial perturbation attacks for ALLM DoS. As audio adversarial attacks have been widely studied, I could not find what makes the proposed method advanced over existing adversarial attack frameworks.
- The discussion of related works is insufficient. Though prior adversarial attacks works on ASR, TTS and ALLMs typically aim at misprediction or jailbreaking rather than DoS, they share relevant adversarial perturbation mechanisms. These related works should be discussed to justify the contribution.
- The imperceptibility claim is not well supported. The paper claims its perturbations are imperceptible, yet I could not find SNR, perceptual metrics or listening tests to back this statement.
- Section 4.5 only tests against additive random noise, which provides a narrow assessment of attack robustness. I would like to see evaluations across common audio processing operations, such as denoising, speech enhancement, resampling and compression for a more realistic evaluation.
- The paper evaluates three models under the same stated experimental setup, yet reports only two in the main results and places Qwen2-Audio in Appendix C. It is not clear to me why the authors chose this presentation layout.
- Figures 2 and 3 are blurry and contain small text that is difficult to read.
Questions for authors
- What technical challenges distinguish DoS attacks on ALLMs from existing audio adversarial attacks, and could the authors clarify how their method address these beyond multi-objective optimization?
- Can the authors provide evaluations of perturbation imperceptibility, such as SNR, PESQ, or listening tests, to assess the trade-off between perturbation magnitude and attack performance?