3 papers
cs.CR2026
Agentic AI Defense: Decode-Time Provenance Binding for MCP
Eric Yocam, Varghese Vaidyan, Paris Kalathas +3
Agentic AI systems using the Model Context Protocol (MCP) are vulnerable to indirect prompt injection through untrusted tool outputs. We demonstrate cross-modal trust laundering, i…
cs.CR2026
AI Security Literacy: Ecosystem-based Competency Framework and K-12 Learning Platform
Eric Yocam, Varghese Vaidyan, Paris Kalathas
Adoption of artificial intelligence in K-12 schools has outpaced guidance for students, teachers, and administrators. Existing AI-literacy frameworks emphasize understanding and us…
cs.CL2026
Adaptive Activation Cancellation for Hallucination Mitigation in Large Language Models
Eric Yocam, Varghese Vaidyan, Gurcan Comert +3
Large Language Models frequently generate fluent but factually incorrect text. We propose Adaptive Activation Cancellation (AAC), a real-time inference-time framework that treats h…