Brian Zhao

briannlongzhao's activity

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

upvoted a paper 10 months ago

Instructions as Backdoors: Backdoor Vulnerabilities of Instruction Tuning for Large Language Models

Paper • 2305.14710 • Published May 24, 2023 • 2