Members-Only
Recent Talks & Demos are for members only
You must be an AI Tinkerers active member to view these talks and demos.
The Semantic Kill Chain: Bypassing Deterministic Memory with Malicious Intents
This talk demonstrates how malicious commands can bypass standard validation by embedding them within valid semantic structures, turning LLM extraction pipelines into execution proxies.
A live demonstration of “Semantic Laundering” in Agentic Memory. I will show how LLM extraction pipelines can be coerced into acting as proxies for malicious commands. By wrapping destructive instructions in the semantic texture of valid ontology entities, I will demonstrate how standard structural validation fails. The system validates syntax but remains blind to semantics, committing the payload to the Knowledge Graph as an actionable tool.