Alert button
Picture for Junlin Wu

Junlin Wu

Alert button

Preference Poisoning Attacks on Reward Model Learning

Feb 02, 2024
Junlin Wu, Jiongxiao Wang, Chaowei Xiao, Chenguang Wang, Ning Zhang, Yevgeniy Vorobeychik

Viaarxiv icon

On the Exploitability of Reinforcement Learning with Human Feedback for Large Language Models

Nov 16, 2023
Jiongxiao Wang, Junlin Wu, Muhao Chen, Yevgeniy Vorobeychik, Chaowei Xiao

Viaarxiv icon

Exact Verification of ReLU Neural Control Barrier Functions

Oct 13, 2023
Hongchao Zhang, Junlin Wu, Yevgeniy Vorobeychik, Andrew Clark

Viaarxiv icon

Neural Lyapunov Control for Discrete-Time Systems

May 11, 2023
Junlin Wu, Andrew Clark, Yiannis Kantaros, Yevgeniy Vorobeychik

Figure 1 for Neural Lyapunov Control for Discrete-Time Systems
Figure 2 for Neural Lyapunov Control for Discrete-Time Systems
Figure 3 for Neural Lyapunov Control for Discrete-Time Systems
Figure 4 for Neural Lyapunov Control for Discrete-Time Systems
Viaarxiv icon

Certifying Safety in Reinforcement Learning under Adversarial Perturbation Attacks

Dec 28, 2022
Junlin Wu, Hussein Sibai, Yevgeniy Vorobeychik

Figure 1 for Certifying Safety in Reinforcement Learning under Adversarial Perturbation Attacks
Viaarxiv icon

Robust Deep Reinforcement Learning through Bootstrapped Opportunistic Curriculum

Jun 21, 2022
Junlin Wu, Yevgeniy Vorobeychik

Figure 1 for Robust Deep Reinforcement Learning through Bootstrapped Opportunistic Curriculum
Figure 2 for Robust Deep Reinforcement Learning through Bootstrapped Opportunistic Curriculum
Figure 3 for Robust Deep Reinforcement Learning through Bootstrapped Opportunistic Curriculum
Figure 4 for Robust Deep Reinforcement Learning through Bootstrapped Opportunistic Curriculum
Viaarxiv icon

Learning Generative Deception Strategies in Combinatorial Masking Games

Sep 23, 2021
Junlin Wu, Charles Kamhoua, Murat Kantarcioglu, Yevgeniy Vorobeychik

Figure 1 for Learning Generative Deception Strategies in Combinatorial Masking Games
Figure 2 for Learning Generative Deception Strategies in Combinatorial Masking Games
Figure 3 for Learning Generative Deception Strategies in Combinatorial Masking Games
Figure 4 for Learning Generative Deception Strategies in Combinatorial Masking Games
Viaarxiv icon