2 papers
cs.SD2026
Expose Your Disguise: Recovering Source Speaker Identity From Voice Conversion
Hanlei Zhang, Zhongming Ma, Mingyang Zhang +3
Voice conversion (VC) poses a significant threat to biometric security by allowing attackers to impersonate target speakers. In forensic contexts, recovering the source speaker's i…
cs.CR2025
Attention is All You Need to Defend Against Indirect Prompt Injection Attacks in LLMs
Yinan Zhong, Qianhao Miao, Yanjiao Chen +3
Large Language Models (LLMs) have been integrated into many applications (e.g., web agents) to perform more sophisticated tasks. However, LLM-empowered applications are vulnerable…