Publications
Parutions, recherche et les travaux qui les ont produites.
Tout ce que KOR IT a publié, et les projets dont les parutions sont issues. Lorsqu'une affirmation est provisoire, la page qui la porte le dit.
Recherche
Les questions rencontrées par l'ingénierie.
Memory Poisoning: When AI Agent Memory Becomes a Security Boundary
Persistent agent memory is an attack surface. We examine provenance, recall policy, and why memory operations remain largely invisible to the SOC.
Sécurité des agents · septembre 2026
Memory Contract Specification
Experimental research, not a standard: can a runtime contract decide when a stored memory entry is permitted to influence an agent's reasoning?
Sécurité des agents · juin 2026
Agent Security: Identity, Tools, Memory and Runtime Policy
An active research programme on agent security: identity and authorisation, tool and MCP inventory, memory, runtime policy, and telemetry.
Sécurité de l'IA · avril 2026
Projets
Les systèmes derrière les écrits.
Agent Security Control Plane
Prototype control plane for governing how agents reach memory, tools, identities and data, with policy and telemetry as first-class layers.
AI Security · Sécurité des agents
Memory Contract Specification
An experimental specification for runtime contracts that decide when a memory record is allowed to influence an agent. Principle: Trust Before Recall.
Agent Memory Security · Sécurité des agents
Sovereign Agentic AI Lab
A self-hosted agentic AI environment on owned hardware, used to study inference, retrieval and agent security without external model dependencies.
AI Infrastructure · Sécurité de l'IA