5 papers
Fragile by Design: On the Limits of Adversarial Defenses in Personalized Generation
Zhen Chen, Yi Zhang, Xiangyu Yin +4
Personalized AI applications such as DreamBooth enable the generation of customized content from user images, but also raise significant privacy concerns, particularly the risk of…
SIDA: Social Media Image Deepfake Detection, Localization and Explanation with Large Multimodal Model
Zhenglin Huang, Jinwei Hu, Xiangtai Li +6
The rapid advancement of generative models in creating highly realistic images poses substantial risks for misinformation dissemination. For instance, a synthetic image, when share…
TAIJI: Textual Anchoring for Immunizing Jailbreak Images in Vision Language Models
Xiangyu Yin, Yi Qi, Jinwei Hu +5
Vision Language Models (VLMs) have demonstrated impressive inference capabilities, but remain vulnerable to jailbreak attacks that can induce harmful or unethical responses. Existi…
Robust RL with LLM-Driven Data Synthesis and Policy Adaptation for Autonomous Driving
Sihao Wu, Jiaxu Liu, Xiangyu Yin +5
The integration of Large Language Models (LLMs) into autonomous driving systems demonstrates strong common sense and reasoning abilities, effectively addressing the pitfalls of pur…
Data Augmentation for Continual RL via Adversarial Gradient Episodic Memory
Sihao Wu, Xingyu Zhao, Xiaowei Huang
Data efficiency of learning, which plays a key role in the Reinforcement Learning (RL) training process, becomes even more important in continual RL with sequential environments. I…