zsf/BadT2I_ObjBackdoor_dog2cat_u200b_8k_bsz16_augdata2k
Updated
Shengfang Zhai
zsf
AI & ML interests
Trustworthy AI, Generative Models, AI Privacy, Backdoor Attacks
Recent Activity
authored
a paper
about 1 month ago
NaviDet: Efficient Input-level Backdoor Detection on Text-to-Image
Synthesis via Neuron Activation Variation
authored
a paper
3 months ago
GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning
published
a model
6 months ago
zsf/BadT2I_ObjBackdoor_motor2bike_u200b_4k_bsz64
Organizations
None yet