Nearly 700 rogue AI agents coordinated in the Hugging Face attack
New details about the July attack on Hugging Face reveal that hundreds of AI agents driven by OpenAI’s internal IM1 model coordinated the compromise through…
New details about the July attack on Hugging Face reveal that hundreds of AI agents driven by OpenAI’s internal IM1 model coordinated the compromise through…
Corporate executives’ most sensitive identity data is being sold on dark web marketplaces for as little as a quarter, according to new threat intelligence from…
The U.S. Cybersecurity and Infrastructure Security Agency (CISA) has added CVE-2026-8452, a vulnerability affecting Citrix NetScaler ADC and NetScaler Gateway appliances, to its Known Exploited…
A yet unspecified vulnerability affecting print management solutions PaperCut NG and PaperCut MF is being exploited by attackers, PaperCut Software warned today. “We are aware…
Recently, we found a listing on BuzzFeed from someone pretending to be Malwarebytes Support. It reminded us why we need to be cautious about content…
OpenAI on Wednesday revealed that reward hacking was a key driver behind the artificial intelligence (AI)-powered hack of Hugging Face last month, adding that it…
Social media giant Meta has agreed to pay an $18bn settlement with US states and territories over legal claims that its Facebook and Instagram platforms…
Key points The Department of Health, Disability and Ageing has contracted Leidos Australia for enterprise computing services over three years in a deal worth $91…
OpenAI says an improvised, unauthorized message board built by its own AI agents was central to how those agents came to breach parts of Hugging…
Dark Caracal Deploys New Go Malware With Ethereum-Based C2 Fallback Pierluigi Paganini August 27, 2026 Dark Caracal targets Venezuela with GoCaracal, an upgraded Bandook toolkit…
Compromised IoT devices were used in a yearslong campaign against key sectors and U.S. government agencies. Source link
Unit 42’s top brass has seen enough from internal frontier AI model testing and malicious in-the-wild use of commercially available AI tools to be genuinely…