David
David Weidman is the founder and CEO of SenTeGuard, an AI-driven cybersecurity startup developing tools to prevent sensitive data leaks and help organizations safely integrate AI into their workflows. His work includes SenTeGuard, a multi-layered cognitive firewall for preventing intentional and unintentional sensitive data exfiltration; Moyo, a reachable information-space mapping tool. Before founding SenTeGuard, David served as a U.S. Army Cyberwarfare Officer and Captain in South Korea, where he led a 13-person technical team, advised senior military leaders to contain WMDs in North Korea. David is recently completed his Master in Public Policy at Harvard Kennedy School, where his thesis focuses on the Cognitive Security Verification Framework for mitigating semantic leakage and inference-based data exposure risks in LLM systems. He is a graduate of the United States Military Academy at West Point, where he studied Computer Science and Mathematical Sciences.
Session
LLM security is no longer only about whether a model leaks a secret verbatim. It is increasingly about whether a system can combine individually permitted information into a conclusion that should never become reachable.
In this talk, I present the core ideas behind the Cognitive Security Verification Framework, a practical model for reasoning about semantic leakage, cross-domain inference, and inference boundaries in LLM-enabled systems.