3 papers
cs.LG2026
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…
cs.LG2026
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…
cs.LG2025
Optimizing the Adversarial Perturbation with a Momentum-based Adaptive Matrix
Wei Tao, Sheng Long, Xin Liu +2
Generating adversarial examples (AEs) can be formulated as an optimization problem. Among various optimization-based attacks, the gradient-based PGD and the momentum-based MI-FGSM…