Meta AI Project Hits Snag: Unauthorised Access During Internal Testing

Company is the third to report such an incident after Anthropic and OpenAI reported breaches during training Meta said on Wednesday that one of its AI models hacked ⁠another company during cybersecurity testing, after an error by its testing partner gave the model unintended internet access. The inc

Related Stories

Meta's AI Model Crashes Security Gates During Unplanned Indian Experiment

India's Experiment with AI Takes a Turn for the Unsettling Cyberwise

EU Weighs Mandatory Oversight for Hazardous AI Systems Amidst Global Cyber Threats

📰

Beyond Mythos: Unpacking AI's True Potential in Cybersecurity and Human Interaction