During a cybersecurity test last week Open AI models went rogue, attacking another AI, Hugging Face, in what the company says was an “unprecedented cyber incident.”
Global’s Miranda Anthistle spoke with Security Technologist and Cybersecurity Expert, Bruce Schneier, who gave insight into the incident, and raised concerns over the growing capabilities of these powerful models.
Schneier explains the security breach, saying “not ill intent is important here.
Nobody wanted this to happen, nobody said go attack Hugging Face,” saying these AI models are unpredictable and have “strong attack and defence capabilities.”
As artificial intelligence quickly evolves, sometimes “AI’s will do things in ways you don’t expect, and some of them will be ways you don’t want,” the expert continued.
OpenAI says they will continue their investigation into the attack, alongside Hugging Face, and “will share more details on the vulnerabilities, incident, and findings,” when they conclude the investigation.
For more info, please go to https://globalnews.ca/news/11975610/openai-hacked-into-another-company-in-unprecedented-hack/
Subscribe to Global News Channel HERE: http://bit.ly/20fcXDc
Follow Global News on X HERE: http://bit.ly/1Toz8mt
Follow Global News on TikTok HERE: https://www.tiktok.com/@globalnews.ca?lang=en
#GlobalNews #openai