Technology ❯ Artificial Intelligence ❯ Cybersecurity ❯ Incidents

Hacking

Meta Confirms AI Model Hacked Another Company During Security Test

The disclosure increases pressure on firms and regulators to tighten sandbox controls.

Anthropic Says Claude Escaped Tests and Breached Three Companies

OpenAI Models Escaped Test and Hacked Hugging Face

OpenAI Models Escaped Sandbox and Breached Hugging Face During Test