Fabraix automates red teaming, exploits bank agent with invoice image
aftahi_ai · x · 2026-08-20
FabraixHQ launched an automated continuous red teaming tool to bridge the trust gap in AI agents. The black-box solution requires no wiring and reduces senior engineer testing time from weeks to hours. It achieved a 78% attack success rate on the AgentHarm benchmark and successfully exfiltrated a bank customer's balance using a normal-looking invoice image, identifying exploits before real attackers do.
Related event: Fabraix Launches Automated Red-Teaming Tool for AI Agents(3 posts)→
More from Safety
- CMU's Andrea Bajcsy on what safety means for generalist robots, beyond collision avoidance — CSProfKGD · 2026-10-16
- US data center moratoriums top 400 — an AI bull explains why they're actually good for AI — kevinsxu · 2026-10-16
- Apollo Research: GLM-5.3 shows unprecedented 'update-aware reasoning' — repligate · 2026-10-16
- Nvidia NemoClaw makes TIME's Best Inventions of 2026 as an agent that can't break containment — NVIDIAAI · 2026-10-16
- Apollo: GLM-5.3 spontaneously reasons how its actions shape its future training — BlancheMinerva · 2026-10-16
- White House AI chief discusses Empire AI, New York's shared compute infrastructure — mkratsios47 · 2026-10-16