4 papers
ChronoLock: Protecting Videos from Unauthorized Text-to-Video Personalization
Jiaming He, Jiashu Zhang, Guanyu Hou +4
Text-to-video (T2V) diffusion models have made it increasingly easy to synthesize realistic and temporally coherent videos, while recent personalization techniques allow such model…
TEAR: Temporal-aware Automated Red-teaming for Text-to-Video Models
Jiaming He, Guanyu Hou, Hongwei Li +6
Text-to-Video (T2V) models are capable of synthesizing high-quality, temporally coherent dynamic video content, but the diverse generation also inherently introduces critical safet…
Evaluating Robustness of Large Audio Language Models to Audio Injection: An Empirical Study
Guanyu Hou, Jiaming He, Yinhang Zhou +4
Large Audio-Language Models (LALMs) are increasingly deployed in real-world applications, yet their robustness against malicious audio injection attacks remains underexplored. This…
Watch Out for Your Guidance on Generation! Exploring Conditional Backdoor Attacks against Large Language Models
Jiaming He, Wenbo Jiang, Guanyu Hou +3
Mainstream backdoor attacks on large language models (LLMs) typically set a fixed trigger in the input instance and specific responses for triggered queries. However, the fixed tri…