Shengfang Zhai

zsf's activity

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

authored a paper 6 days ago

NaviDet: Efficient Input-level Backdoor Detection on Text-to-Image Synthesis via Neuron Activation Variation

Paper • 2503.06453 • Published Mar 9

authored a paper 2 months ago

GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning

Paper • 2505.11049 • Published May 16 • 61

authored a paper 6 months ago

GuardReasoner: Towards Reasoning-based LLM Safeguards

Paper • 2501.18492 • Published Jan 30 • 88

authored 2 papers 7 months ago

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

Paper • 2305.04175 • Published May 7, 2023 • 1

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

Paper • 2405.14800 • Published May 23, 2024 • 1