Junlin Wu

Publication Activity (10 Years)

Years Active: 2022-2024
Publications (10 Years): 15

Top Topics

Function Approximators

Detecting Malicious

Reinforcement Learning

Top Venues

Publications

Junlin Wu, Hussein Sibai, Yevgeniy Vorobeychik
Certifying Safety in Reinforcement Learning under Adversarial Perturbation Attacks. SP (Workshops) (2024)
Junlin Wu, Jiongxiao Wang, Chaowei Xiao, Chenguang Wang, Ning Zhang, Yevgeniy Vorobeychik
Preference Poisoning Attacks on Reward Model Learning. CoRR (2024)
Jiongxiao Wang, Junlin Wu, Muhao Chen, Yevgeniy Vorobeychik, Chaowei Xiao
RLHFPoison: Reward Poisoning Attack for Reinforcement Learning with Human Feedback in Large Language Models. ACL (1) (2024)
Luise Ge, Daniel Halpern, Evi Micha, Ariel D. Procaccia, Itai Shapira, Yevgeniy Vorobeychik, Junlin Wu
Axioms for AI Alignment from Human Feedback. CoRR (2024)
Junlin Wu, Huan Zhang, Yevgeniy Vorobeychik
Verified Safe Reinforcement Learning for Neural Network Dynamic Models. CoRR (2024)
Hongchao Zhang, Junlin Wu, Yevgeniy Vorobeychik, Andrew Clark
Exact Verification of ReLU Neural Control Barrier Functions. CoRR (2023)
Jiongxiao Wang, Junlin Wu, Muhao Chen, Yevgeniy Vorobeychik, Chaowei Xiao
On the Exploitability of Reinforcement Learning with Human Feedback for Large Language Models. CoRR (2023)
Junlin Wu, Andrew Clark, Yiannis Kantaros, Yevgeniy Vorobeychik
Neural Lyapunov Control for Discrete-Time Systems. NeurIPS (2023)
Junlin Wu, Andrew Clark, Yiannis Kantaros, Yevgeniy Vorobeychik
Neural Lyapunov Control for Discrete-Time Systems. CoRR (2023)
Hongchao Zhang, Junlin Wu, Yevgeniy Vorobeychik, Andrew Clark
Exact Verification of ReLU Neural Control Barrier Functions. NeurIPS (2023)
Junlin Wu, Andrew Estornell, Lecheng Kong, Yevgeniy Vorobeychik
Manipulating Elections by Changing Voter Perceptions. CoRR (2022)
Junlin Wu, Andrew Estornell, Lecheng Kong, Yevgeniy Vorobeychik
Manipulating Elections by Changing Voter Perceptions. IJCAI (2022)
Junlin Wu, Hussein Sibai, Yevgeniy Vorobeychik
Certifying Safety in Reinforcement Learning under Adversarial Perturbation Attacks. CoRR (2022)
Junlin Wu, Yevgeniy Vorobeychik
Robust Deep Reinforcement Learning through Bootstrapped Opportunistic Curriculum. ICML (2022)
Junlin Wu, Yevgeniy Vorobeychik
Robust Deep Reinforcement Learning through Bootstrapped Opportunistic Curriculum. CoRR (2022)