Yang Ouyang

OriDragon2000's activity

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

authored a paper 9 months ago

Layer-Level Self-Exposure and Patch: Affirmative Token Mitigation for Jailbreak Attack Defense

Paper • 2501.02629 • Published Jan 5 • 1

authored a paper over 1 year ago

Min-K%++: Improved Baseline for Detecting Pre-Training Data from Large Language Models

Paper • 2404.02936 • Published Apr 3, 2024 • 3