Shengfang Zhai's picture

3

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

authored a paper 5 days ago

GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning

published a model 3 months ago

zsf/BadT2I_ObjBackdoor_motor2bike_u200b_4k_bsz64

upvoted a paper 3 months ago

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

View all activity

Organizations

None yet

zsf's activity

upvoted 2 papers 3 months ago

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

Paper • 2405.14800 • Published May 23, 2024 • 1

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

Paper • 2305.04175 • Published May 7, 2023 • 1

upvoted a paper 4 months ago

GuardReasoner: Towards Reasoning-based LLM Safeguards

Paper • 2501.18492 • Published Jan 30 • 87