Cyber Attacks
Verify AI training environments are air-gapped per researcher warning
Hundreds of AI experts urge immediate isolation of cyber-capable model training systems to prevent potential security breaches and containment failures.
AI security
Everything Malware Chronicle has reported about AI security: 2 stories, newest first. Part of our Cyber Attacks coverage.
Cyber Attacks
Cyber Attacks
Verify AI Model Integrity After Hugging Face Hack
Nvidia releases new open-weight models as teams assess security risks following the recent Hugging Face incident.