John Halloran

johnhalloran's activity

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

commented 2 papers 16 days ago

MCP Safety Training: Learning to Refuse Falsely Benign MCP Exploits using Improved Preference Alignment

Paper • 2505.23634 • Published May 29, 2025 •

1

Leveraging RAG for Training-Free Alignment of LLMs

Paper • 2605.11217 • Published May 11 •

1

commented a paper over 1 year ago

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

Paper • 2504.03767 • Published Apr 2, 2025 • 3 •

3