Jan Wehner

Institute for AI Policy and Strategy †Existential Risk Alliance ‡Singapore AI Safety Hub

Papers on Lattice

Total citations

Topics

Research focus

Red-Teaming & Adversarial Robustness (1)Tool Use & Agents (1)

Frequent co-authors

Matt Mittelsteadt (1)Jam Kraprayoon (1)Robin Staes-Polet (1)Oskar Galeev (1)Christopher Covino (1)Shaun Ee (1)

Papers (1)

May 21, 2026

Institute for AI Policy and StrategyMay 21, 2026·also Research lead(s

Detecting Offensive Cyber Agents: A Detection-in-Depth Approach

Current cybersecurity is unprepared for the coming wave of AI-orchestrated cyberattacks, necessitating a strategic shift towards "detection-in-depth" to counter autonomous offensive agents.

Matt Mittelsteadt, Jam Kraprayoon, Robin Staes-Polet +4

Red-Teaming & Adversarial Robustness Tool Use & Agents

Jan Wehner

Research focus

Frequent co-authors

Papers (1)

Search

Jan Wehner

Research focus

Frequent co-authors

Papers (1)