6 papers
Reinforcement Learning for Self-Improving Agent with Skill Library
Jiongxiao Wang, Qiaojing Yan, Yawei Wang +6
Large Language Model (LLM)-based agents have demonstrated remarkable capabilities in complex reasoning and multi-turn interactions but struggle to continuously improve and adapt wh…
Robust Representation Consistency Model via Contrastive Denoising
Jiachen Lei, Julius Berner, Jiongxiao Wang +5
Robustness is essential for deep neural networks, especially in security-sensitive applications. To this end, randomized smoothing provides theoretical guarantees for certifying ro…
Benchmarking Vision Language Model Unlearning via Fictitious Facial Identity Dataset
Yingzi Ma, Jiongxiao Wang, Fei Wang +10
Machine unlearning has emerged as an effective strategy for forgetting specific information in the training data. However, with the increasing integration of visual data, privacy c…
Test-time Backdoor Mitigation for Black-Box Large Language Models with Defensive Demonstrations
Wenjie Mo, Jiashu Xu, Qin Liu +5
Existing studies in backdoor defense have predominantly focused on the training phase, overlooking the critical aspect of testing time defense. This gap becomes pronounced in the c…
FATH: Authentication-based Test-time Defense against Indirect Prompt Injection Attacks
Jiongxiao Wang, Fangzhou Wu, Wendi Li +5
Large language models (LLMs) have been widely deployed as the backbone with additional tools and text information for real-world applications. However, integrating external informa…
Preference Poisoning Attacks on Reward Model Learning
Junlin Wu, Jiongxiao Wang, Chaowei Xiao +3
Learning reward models from pairwise comparisons is a fundamental component in a number of domains, including autonomous control, conversational agents, and recommendation systems,…