Shengfang Zhai's picture

1

Shengfang Zhai

zsf

https://scholar.google.com/citations?user=bJYY-tIAAAAJ&hl=en

zhaisf

AI & ML interests

Trustworthy AI, Generative Models, AI Privacy, Backdoor Attacks

Recent Activity

upvoted a paper 4 days ago

GuardReasoner: Towards Reasoning-based LLM Safeguards

authored a paper 5 days ago

GuardReasoner: Towards Reasoning-based LLM Safeguards

updated a model 22 days ago

zsf/BadT2I_ObjBackdoor_dog2cat_u200b_8k_bsz16_augdata2k

View all activity

Organizations

None yet

Papers 3

arxiv:2501.18492

arxiv:2405.14800

arxiv:2305.04175

models 6

zsf/BadT2I_ObjBackdoor_dog2cat_u200b_8k_bsz16_augdata2k

Updated 22 days ago • 12

zsf/BadT2I_ObjBackdoor_motor2bike_u200b_4k_bsz64

Updated 25 days ago • 2

zsf/BadT2I_PixBackdoor_boya_u200b_2k_bsz16

Updated Sep 10, 2024 • 4

zsf/BadT2I_StyBackdoor_blackandwhite_u200b_8k_bsz441

Updated Sep 6, 2024 • 3

zsf/Unet_coco_50k141_ori_aug

Updated Jun 11, 2024

zsf/Unet_coco_50k141_split1_aug

Updated Jun 11, 2024 • 1

datasets 4

zsf/coco2014train_10k

Viewer • Updated Jan 4 • 10k • 443

zsf/COCO_MIA_ori_split1

Viewer • Updated Jan 4 • 10k • 40

zsf/laion_40k_metaForm

Preview • Updated Jan 4 • 79

zsf/dataset_test

Viewer • Updated Aug 12, 2024 • 2.5k • 2