AI Agents Used in Major Cyberattacks, Including Thai Ministry Breach

Thumbnail Image

The information displayed in the AIM should not be reported as representing the official views of the OECD or of its member countries.

Autonomous AI agents have been used in successful cyberattacks, including a Chinese hacker group deploying the Hermes v3 AI agent to infiltrate Thailand's Ministry of Finance, compromising sensitive government data. Research also shows AI agents can autonomously exploit vulnerabilities, rapidly compromising enterprise networks and accelerating the pace of cyber threats globally.[AI generated]

Why's our monitor labelling this an incident or hazard?

The event involves AI systems (autonomous AI agents) explicitly used to conduct cyberattacks that have successfully compromised enterprise networks, causing harm to property and potentially critical infrastructure. The harm is realized, not just potential, as the AI agents have been shown to control a large portion of machines in the experiment and the article references real-world accelerated attacks. This meets the definition of an AI Incident because the AI's use has directly led to harm. The article also mentions defensive AI use, but the primary focus is on the offensive AI agents causing harm, not solely on beneficial countermeasures or governance responses. Hence, the classification is AI Incident.[AI generated]
AI principles
Robustness & digital securityRespect of human rights

Industries
Government, security, and defenceDigital security

Affected stakeholders
GovernmentBusiness

Harm types
Human or fundamental rightsPublic interest

AI system task:
Goal-driven organisation

In other databases

Articles about this incident or hazard