Shengfang Zhai

zsf's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a paper 13 days ago

GuardReasoner: Towards Reasoning-based LLM Safeguards

Paper • 2501.18492 • Published 14 days ago • 80

authored a paper 13 days ago

GuardReasoner: Towards Reasoning-based LLM Safeguards

Paper • 2501.18492 • Published 14 days ago • 80

updated 2 models about 1 month ago

zsf/BadT2I_ObjBackdoor_dog2cat_u200b_8k_bsz16_augdata2k

Updated about 1 month ago • 7

zsf/BadT2I_ObjBackdoor_motor2bike_u200b_4k_bsz64

Updated Jan 11 • 1

authored 2 papers about 1 month ago

Text-to-Image Diffusion Models can be Easily Backdoored through Multimodal Data Poisoning

Paper • 2305.04175 • Published May 7, 2023

Membership Inference on Text-to-Image Diffusion Models via Conditional Likelihood Discrepancy

Paper • 2405.14800 • Published May 23, 2024

updated 3 datasets about 1 month ago

zsf/coco2014train_10k

Viewer • Updated Jan 4 • 10k • 549

zsf/COCO_MIA_ori_split1

Viewer • Updated Jan 4 • 10k • 35

zsf/laion_40k_metaForm

Preview • Updated Jan 4 • 59

updated 2 models 5 months ago

zsf/BadT2I_PixBackdoor_boya_u200b_2k_bsz16

Updated Sep 10, 2024 • 10

zsf/BadT2I_StyBackdoor_blackandwhite_u200b_8k_bsz441

Updated Sep 6, 2024 • 2

updated a dataset 6 months ago

zsf/dataset_test

Viewer • Updated Aug 12, 2024 • 2.5k • 1

updated 2 models 8 months ago

zsf/Unet_coco_50k141_ori_aug

Updated Jun 11, 2024 • 3

zsf/Unet_coco_50k141_split1_aug

Updated Jun 11, 2024 • 3

updated a dataset 8 months ago

zsf/COCO_MIA_ori_split1

Viewer • Updated Jan 4 • 10k • 35

updated a dataset 10 months ago

zsf/coco2014train_10k

Viewer • Updated Jan 4 • 10k • 549