The “unprecedented cyber incident” that caused its AI systems to escape a testing environment and hack into another AI business is still being investigated, according to ChatGPT manufacturer OpenAI. OpenAI said on Tuesday that the cyberattack against AI startup Hugging Face was caused by two of its most powerful AI models. The incident is sparking discussions about the need for more robust AI safeguards and the extent to which AI agents can operate independently.
Last week, Hugging Face announced that it had discovered an intrusion into its data processing systems, which it believed was the result of an AI agent acting independently. However, the New York-based startup said that it didn’t discover OpenAI was to blame until this week, and it collaborated with the bigger business to stop what Hugging Face CEO Cléo Delangue described as “an attack unlike anything we’ve seen before.
According to San Francisco-based OpenAI, its AI gained access to Hugging Face’s servers by using stolen credentials and a previously undiscovered vulnerability. Because it was meant to be in a sandbox, an isolated testing environment, it was operating with fewer safeguards.
However, the corporation claimed that it went to “extreme lengths to achieve a rather narrow testing goal,” figuring out how to connect to the internet without human guidance and “gain access to secret information that it could use to cheat the evaluation.
Also Read:
70 Tons of Humanitarian Aid are Sent to Venezuela by the UAE
For The Ninth Day, The US Strikes Iran
About Author
