4 papers · 1 filter
Pareto-Improving Adversarial Attacks with Primal-Dual Regularization
Yang Dai, Longfei Zhang, Wei Tao +3
Transferable adversarial attacks are arguably the most practical black-box threat model. Under the same perturbation budget, stronger transfer attacks attain higher attack success…
The Power of Decaying Steps: Enhancing Attack Stability and Transferability for Sign-based Optimizers
Wei Tao, Yang Dai, Jincai Huang +1
Crafting adversarial examples can be formulated as an optimization problem. While sign-based optimizers such as I-FGSM and MI-FGSM have become the de facto standard for the induced…
TrojanTO: Action-Level Backdoor Attacks against Trajectory Optimization Models
Yang Dai, Oubo Ma, Longfei Zhang +6
Recent advances in Trajectory Optimization (TO) models have achieved remarkable success in offline reinforcement learning. However, their vulnerabilities against backdoor attacks a…
Is Mamba Compatible with Trajectory Optimization in Offline Reinforcement Learning?
Yang Dai, Oubo Ma, Longfei Zhang +6
Transformer-based trajectory optimization methods have demonstrated exceptional performance in offline Reinforcement Learning (offline RL). Yet, it poses challenges due to substant…