Showing cs.CRShow all
3 papers · 1 filter
cs.CR2026
Aegis: Towards Governance, Integrity, and Security of AI Voice Agents
Xiang Li, Pin-Yu Chen, Wenqi Wei
With the rapid advancement and adoption of Audio Large Language Models (ALLMs), voice agents are now being deployed in high-stakes domains such as banking, customer service, and IT…
cs.CR2025
Measuring the Robustness of Audio Deepfake Detection under Real-World Corruption
Xiang Li, Pin-Yu Chen, Wenqi Wei
Deepfakes have emerged as a widespread and rapidly escalating concern in generative AI, spanning images, audio, and videos. Among these, audio deepfakes are particularly alarming d…
cs.CR2024
AutoJailbreak: Exploring Jailbreak Attacks and Defenses through a Dependency Lens
Lin Lu, Hai Yan, Zenghui Yuan +4
Jailbreak attacks in large language models (LLMs) entail inducing the models to generate content that breaches ethical and legal norm through the use of malicious prompts, posing a…