Follow
Guanlin Liu
Guanlin Liu
University of Califonia, Davis
Verified email at ucdavis.edu
Title
Cited by
Cited by
Year
Provably efficient black-box action poisoning attacks against reinforcement learning
G Liu, L Lai
Advances in Neural Information Processing Systems 34, 12400-12410, 2021
322021
Action-manipulation attacks on stochastic bandits
G Liu, L Lai
ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and …, 2020
252020
Action-manipulation attacks against stochastic bandits: Attacks and defense
G Liu, L Lai
IEEE Transactions on Signal Processing 68, 5152-5165, 2020
172020
Efficient adversarial attacks on online multi-agent reinforcement learning
G Liu, L Lai
Advances in Neural Information Processing Systems 36, 2024
42024
Efficient action poisoning attacks on linear contextual bandits
G Liu, L Lai
arXiv preprint arXiv:2112.05367, 2021
32021
Optimal cost constrained adversarial attacks for multiple agent systems
Z Lu, G Liu, L Lai, W Xu
2024 58th Annual Conference on Information Sciences and Systems (CISS), 1-6, 2024
12024
Camouflage Adversarial Attacks on Multiple Agent Systems
Z Lu, G Liu, L Lai, W Xu
arXiv preprint arXiv:2401.17405, 2024
12024
Action Poisoning Attacks on Linear Contextual Bandits
G Liu, L Lai
Transactions on Machine Learning Research, 2022
12022
Reward Attack on Stochastic Bandits with Non-Stationary Rewards
C Yang, G Liu, L Lai
2023 57th Asilomar Conference on Signals, Systems, and Computers, 1387-1393, 2023
2023
Efficient Action Robust Reinforcement Learning with Probabilistic Policy Execution Uncertainty
G Liu, Z Zhou, H Liu, L Lai
arXiv preprint arXiv:2307.07666, 2023
2023
The system can't perform the operation now. Try again later.
Articles 1–10