Anthropic's Claude Mitos AI Withheld Over Cybersecurity Risks and Unauthorized Access

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.

Anthropic's advanced AI model, Claude Mitos, demonstrated exceptional cybersecurity capabilities, raising concerns about its potential misuse for cyberattacks on critical infrastructure. Unauthorized users accessed the system without permission, prompting investigations. Fearing significant risks, Anthropic withheld public release, limiting access to select organizations for defensive purposes.[AI generated]

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

The AI system's development and potential use could plausibly lead to serious harm, specifically disruption of critical infrastructure or systems via cyberattacks. Although no actual harm has been reported yet, the article clearly states the risk is significant enough to withhold public release. Therefore, this event fits the definition of an AI Hazard, as it involves an AI system whose capabilities could plausibly lead to an AI Incident involving harm to critical infrastructure or systems.[AI generated]
AI principles
Robustness & digital securitySafety
Industries
Digital securityGovernment, security, and defence
Affected stakeholders
GovernmentGeneral public
Harm types
Public interest
Business function:
ICT management and information security
AI system task:
Event/anomaly detection

Articles about this incident or hazard