Yvonne Smith

yvonsmith's activity

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

upvoted 2 papers 11 days ago

What Gradients Add to Text Leakage in Split Language Models, Counted per Token and per Document

Paper • 2610.04128 • Published Oct 2 • 9

Privacy Failure in Split-LLM Training, The Returned Gradient Nullifies the Decoys

Paper • 2609.04382 • Published Sep 3 • 6

upvoted a paper 12 days ago

The LLM-Attacker: A Unified Red-Team Framework for Privacy Evaluation of Split and Distributed LLM Systems

Paper • 2610.22722 • Published 21 days ago • 7