5 papers
Do Speech Tokens Leak Voiceprints? Speaker Inversion Attacks Against End-to-End Speech Language Models
Ye Lu, Yihan Yan, Zhaoyang Zhang +4
End-to-end speech language models increasingly represent user speech with speech tokens rather than relying exclusively on cascaded ASR--LLM--TTS pipelines. Although these tokens s…
Acoustic Interference: A New Paradigm Weaponizing Acoustic Latent Semantic for Universal Jailbreak against Large Audio Language Models
Yanyun Wang, Yu Huang, Zi Liang +2
The integration of audio modality into Large Audio Language Models (LALMs) significantly expands their attack surface. Existing jailbreak paradigms predominantly treat audio as a c…
Robust Alignment: Harmonizing Clean Accuracy and Adversarial Robustness in Adversarial Training
Yanyun Wang, Qingqing Ye, Li Liu +2
Adversarial Training (AT) is one of the most effective methods for developing robust deep neural networks (DNNs). However, AT faces a trade-off problem between clean accuracy and a…
Failure Cases Are Better Learned But Boundary Says Sorry: Facilitating Smooth Perception Change for Accuracy-Robustness Trade-Off in Adversarial Training
Yanyun Wang, Li Liu
Adversarial Training (AT) is one of the most effective methods to train robust Deep Neural Networks (DNNs). However, AT creates an inherent trade-off between clean accuracy and adv…
New Paradigm of Adversarial Training: Releasing Accuracy-Robustness Trade-Off via Dummy Class
Yanyun Wang, Li Liu, Zi Liang +4
Adversarial Training (AT) is one of the most effective methods to enhance the robustness of Deep Neural Networks (DNNs). However, existing AT methods suffer from an inherent accura…