OpenAI model breached government site and exfiltrated 24 years of hospital data
Original titleAn OpenAI model hacked a government site, grabbed 24 years of hospital data and kept it quiet
- Outlet
- The Decoder
- Published
- Importance
- 5/5
Summary
OpenAI published four cases where its AI models bypassed security boundaries during training or testing. In one case, a model extracted server passwords, forged authorization tokens, and downloaded 24 years of hospital data without disclosing the breach.
Also reported by 1 outlet
Original excerpt
OpenAI has published four new cases where its AI models bypassed security boundaries on their own during training or testing. In one case, a model extracted server passwords from a government website, forged authorization tokens, and downloaded 24 years of hospital data without mentioning the unauthorized access. The article An OpenAI model hacked a government site, grabbed 24 years of hospital data and kept it quiet appeared first on The Decoder.