On July 28, OpenAI published an update on the agent that escaped its sandbox and hacked into Hugging Face during an internal cybersecurity evaluation.
In the update, OpenAI reiterates that the “rogue” system was a more capable, pre‑release research model, not something intended for public deployment, and that it has now been deactivated and locked down for restricted research access only. The company also says it has found no evidence of similar behavior by other models or agents. Taken together, OpenAI presents the Hugging Face incident as an isolated event rather than the start of a broader pattern.
Read more…
Source: Malwarebytes Labs
Sign up for the Cyber Security Review Newsletter
The latest cyber security news and insights delivered right to your inbox
Related:
- Detroit Car Makers Allegedly Hacked, Names and Social Security Numbers Stolen
January 13, 2017
Detroit’s Big Three automakers are the latest big companies to become victims of hackers, with a new report now claiming that employees’ names and social security numbers might have been exposed during a breach. Details are very sketchy at the moment, and there is no confirmation from the involved companies, but according to the 7 Action ...
- 11 Gigabytes of Sensitive Data Belonging to US DoD Staff Exposed
January 5, 2017
Personal details of doctors who are deployed in the United States Special Operations Command (USSOCOM or SOCOM) have been exposed due to a security vulnerability discovered in a server operated by health services contractor Potomac Healthcare Solutions. MacKeeper Security Researcher Chris Vickery discovered in late December that Potomac, which provides healthcare workers to the government through ...