2 papers
cs.CR2025
When and Where do Data Poisons Attack Textual Inversion?
Jeremy Styborski, Mingzhi Lyu, Jiayou Lu +2
Poisoning attacks pose significant challenges to the robustness of diffusion models (DMs). In this paper, we systematically analyze when and where poisoning attacks textual inversi…
cs.CV2024
Exploiting Supervised Poison Vulnerability to Strengthen Self-Supervised Defense
Jeremy Styborski, Mingzhi Lyu, Yi Huang +1
Availability poisons exploit supervised learning (SL) algorithms by introducing class-related shortcut features in images such that models trained on poisoned data are useless for…