arxiv:2501.18492
Shengfang Zhai
zsf
AI & ML interests
Trustworthy AI, Generative Models, AI Privacy, Backdoor Attacks
Recent Activity
upvoted
a
paper
9 days ago
GuardReasoner: Towards Reasoning-based LLM Safeguards
authored
a paper
9 days ago
GuardReasoner: Towards Reasoning-based LLM Safeguards
updated
a model
27 days ago
zsf/BadT2I_ObjBackdoor_dog2cat_u200b_8k_bsz16_augdata2k
Organizations
None yet
Papers
3
models
6
zsf/BadT2I_ObjBackdoor_dog2cat_u200b_8k_bsz16_augdata2k
Updated
•
13
zsf/BadT2I_ObjBackdoor_motor2bike_u200b_4k_bsz64
Updated
•
1
zsf/BadT2I_PixBackdoor_boya_u200b_2k_bsz16
Updated
•
4
zsf/BadT2I_StyBackdoor_blackandwhite_u200b_8k_bsz441
Updated
•
3
zsf/Unet_coco_50k141_ori_aug
Updated
•
1
zsf/Unet_coco_50k141_split1_aug
Updated
•
1