Showing cs.SDShow all
2 papers · 1 filter
cs.SD2026
AudioGuard: Toward Comprehensive Audio Safety Protection Across Diverse Threat Models
Mintong Kang, Chen Fang, Bo Li
Audio has rapidly become a primary interface for foundation models, powering real-time voice assistants. Ensuring safety in audio systems is inherently more complex than just "unsa…
cs.SD2024
AdvWave: Stealthy Adversarial Jailbreak Attack against Large Audio-Language Models
Mintong Kang, Chejian Xu, Bo Li
Recent advancements in large audio-language models (LALMs) have enabled speech-based user interactions, significantly enhancing user experience and accelerating the deployment of L…