الباحثون

Longfei Zhang

المنشورات 1

نسخة أولية وصول مفتوح

Pareto-Improving Adversarial Attacks with Primal-Dual Regularization

Yang Dai, Longfei Zhang, Wei Tao وآخرون · 2026

Transferable adversarial attacks are arguably the most practical black-box threat model. Under the same perturbation budget, stronger transfer attacks attain higher attack success rate (ASR), yet their imperceptibility also tends to degrade. Under such a fixed-budget protocol, transferability and imperceptibility there …

المؤلفون المشاركون