4 papers
Once Poisoned, Arbitrarily Controlled: A Programmable Backdoor in VLMs
Tao Lin, Gaojie Jin, Zongxin Liu +2
Existing vision-language model (VLM) backdoors are usually treated as static vulnerabilities: one-to-one and N-to-N attacks bind one or more triggers to a finite set of targets bef…
TrajRS: Towards Certified Robustness in Pedestrian Trajectory Prediction
Liang Zhang, Gaojie Jin, Yao Shi +4
The robustness of trajectory prediction models is crucial for developing safe autonomous driving systems. Adversarial attacks on trajectory prediction can significantly impair the…
BadThink: Triggered Overthinking Attacks on Chain-of-Thought Reasoning in Large Language Models
Shuaitong Liu, Renjue Li, Lijia Yu +3
Recent advances in Chain-of-Thought (CoT) prompting have substantially improved the reasoning capabilities of large language models (LLMs), but have also introduced their computati…
Preference Alignment on Diffusion Model: A Comprehensive Survey for Image Generation and Editing
Sihao Wu, Xiaonan Si, Chi Xing +5
The integration of preference alignment with diffusion models (DMs) has emerged as a transformative approach to enhance image generation and editing capabilities. Although integrat…