Threat Modelling for Sleeper Agents in Agentic AI: Attack Chains and Resilience for Digital Identity Systems
A workshop focused on threat modelling to counter systemic cyber risks from combining shadow AI, sleeper agents, malware and disinformation in autonomous AI attacks in digital identity systems.
Time & Location
26 Nov 2025, 10:00 – 13:00
Online
About the event
Together with The Alan Turing Institute, we invite you to our upcoming workshop, 'Threat Modelling for Sleeper Agents in Agentic AI: Attack Chains and Resilience for Digital Identity Systems'.
This workshop advances the ongoing exploration of systemic cyber risks in digital identity infrastructures, building directly on insights gained from Workshop 1 (Rapid Evidence Review) and Workshop 2 (Resilience in Digital Identity – Systemic Risks from Emerging Technologies). While the earlier sessions mapped the broader landscape of risks and resilience challenges, Workshop 3 focuses on developing threat models to understand and counter the convergence of Shadow AI, sleeper agents, AI malware, and AI based disinformation within autonomous AI-driven attacks.
The session will also consider the role of emerging protocols such as Model Context Protocol (MCP), Agent-to-Agent (A2A), and AGNTCY, which are reshaping how agents interact, coordinate, and embed within digital infrastructures, and which may inadvertently introduce new systemic vulnerabilities.