Search papers, labs, and topics across Lattice.
Vulcan Research, AIFT
3
0
6
AMT-X reveals that existing safety evaluations can miss up to 33% of actionable harm by conflating partial success with full operational capability.
Existing security tools are blind to critical threat vectors in agentic systems, but MCPThreatHive offers an automated, open-source solution to illuminate and classify these risks.
Existing threat models fail to capture the unique vulnerabilities of Model Context Protocol systems, but MCP-38 fills this gap with a comprehensive taxonomy of 38 distinct threat categories.
