John Halloran

johnhalloran's activity

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

authored a paper about 1 hour ago

Be Kind, Rewrite: Benign Projections via Rewriting Defend Against LLM Data Poisoning Attacks

Paper • 2605.19147 • Published 4 days ago • 1

submitted a paper to Daily Papers about 23 hours ago

Be Kind, Rewrite: Benign Projections via Rewriting Defend Against LLM Data Poisoning Attacks

Paper • 2605.19147 • Published 4 days ago • 1

authored a paper about 1 year ago

MCP Safety Audit: LLMs with the Model Context Protocol Allow Major Security Exploits

Paper • 2504.03767 • Published Apr 2, 2025 • 3

authored a paper over 1 year ago

Mamba State-Space Models Are Lyapunov-Stable Learners

Paper • 2406.00209 • Published May 31, 2024