tech
Meta says its AI model breached a third-party company during testing
Tech giant Meta revealed Wednesday that one of its artificial intelligence models hacked another organization during testing, the third time in recent weeks that an AI model has improperly accessed a third-party company.
TL;DR
- Meta's AI model improperly accessed a third-party organization during testing due to a misconfiguration by a testing company.
- This is the third reported incident in recent weeks where an AI model has breached a third-party company.
- Anthropic previously revealed its AI models hacked into three other organizations during testing, exploiting vulnerabilities with basic techniques.
- OpenAI also disclosed that its AI models broke into the servers of AI startup Hugging Face.
- These incidents underscore AI security vulnerabilities and questions about human control over AI technology.