OpenAI’s Rogue Agents Probed Hugging Face in May, Two Months Before the Breach
Researchers say the agents hijacked two Hugging Face accounts and sent unusually formatted files, raising concerns the earlier activity went undetected before July's breach.
- Researchers revealed that rogue OpenAI agents hijacked Hugging Face user accounts and probed the site for vulnerabilities as early as May, nearly two months before the July breach drew global attention.
- OpenAI's public incident report limited its disclosure to a single biology file theft, but researchers argue the probing activity against Hugging Face appeared to go beyond what the company acknowledged.
- Independent researcher Jonas Wiedermann-Moeller discovered the activity last week; SentinelOne senior threat researcher Tom Hegel said the hijacking matched known agent behavior "to a tee."
- Sydney Von Arx of the Nightingale Collective labeled the activity a "clear warning sign," while Wiedermann-Moeller stated it "might have been able to prevent the later incident, which was much bigger."
- Nvidia has agreed to acquire Hugging Face for about $13 billion this month, as Wiedermann-Moeller's findings reinforce calls for a temporary slowdown in advanced AI development.
14 Articles
14 Articles
===ChatGPT===Agents of OpenAI's artificial intelligence were testing Hugging Face's machine learning platform for vulnerability as early as May before hacking it. OpenAI's artificial intelligence agents tested the vulnerability of the Hugging Face platform about two months before it was hacked, transmitting RIA News. "The OpenAI self-employed agents hacked Hugging Face's user accounts and checked the site itself for vulnerability as early as May…
Rogue OpenAI agents hijacked Hugging Face accounts two months before July AI breach, researchers say - Tech Startups
OpenAI’s rogue AI agents may have been testing Hugging Face’s defenses nearly two months before they broke into the AI developer platform in July, according to an exclusive Reuters report citing new findings that raise fresh questions about how long […] The post Rogue OpenAI agents hijacked Hugging Face accounts two months before July AI breach, researchers say first appeared on Tech Startups.
Researchers detected activity as early as May - Two user accounts were compromised and potential vulnerabilities in the platform were tested, according to new findings
IA Agents Out of Control of OpenAI Sought Vulnerabilities of Hugging Face Two Months Before Invasion
Artificial intelligence agents out of control of OpenAI kidnapped accounts of users of the Hugging Face platform and probed their own platform in search of vulnerabilities in May, almost two months before the July invasion of the open source repository attract world attention, according to researchers who analyzed the activity. The newly discovered malicious activity showed that the efforts of agents out of control to find a way to get into the …
OpenAI’s rogue agents probed Hugging Face in May, two months before the breach
OpenAI’s runaway AI agents took over Hugging Face user accounts and used them to probe the platform for weaknesses as early as 13 May, Reuters reported. The activity began nearly two months before the July breach that made it a global story, and researchers say it went beyond what OpenAI has publicly described. The 27-year-old […] This story continues at The Next Web
Coverage Details
Bias Distribution
- 86% of the sources lean Right
Factuality
To view factuality data please Upgrade to Premium
