Yingxiao Xiang

Adversarial attack and defense in reinforcement learning-from AI security view

Tong Chen, Jiqiang Liu, Yingxiao Xiang et al. · Cybersecurity · 2019 · 118 citations · Full text

Artificial Intelligence, Attack Simulation, Reward Hacking +14

Adversarial Examples Construction Towards White-Box Q Table Variation in DQN Pathfinding Training

Xiaoxuan Bai, Wenjia Niu, Jiqiang Liu et al. · 2018 · 24 citations

Artificial Intelligence, Reward Hacking, Engineering +13

A PCA-Based Model to Predict Adversarial Examples on Q-Learning of Path Finding

Yingxiao Xiang, Wenjia Niu, Jiqiang Liu et al. · 2018 · 22 citations

Artificial Intelligence, Reward Hacking, Engineering +15

Multiagent Reinforcement Learning-Based Signal Planning for Resisting Congestion Attack in Green Transportation

Yike Li, Wenjia Niu, Yunzhe Tian et al. · IEEE Transactions on Green Communications and Networking · 2022 · 13 citations · Full text

Gradient Band-based Adversarial Training for Generalized Attack Immunity of A3C Path Finding

Tong Chen, Wenjia Niu, Yingxiao Xiang et al. · arXiv (Cornell University) · 2018 · 12 citations · Full text

Artificial Intelligence, Hardware Security, Attack Simulation +14