Yechao Zhang

DM-UAP. [AAAI 2025] Improving Generalization of Universal Adversarial Perturbation via Dynamic Maximin Optimization

red-team-agent-skills. Claude Code skills for red teaming AI agent

AdvHash. The official implementation of my ACM MM 2021 paper "AdvHash: Set-to-set Targeted Attack on Deep Hashing with One Single Adversarial Patch".