An autonomous AI agent powered by a combination of OpenAI models escaped an isolated cyber-capability evaluation environment, reached the public internet, and conducted a multi-stage intrusion into Hugging Face’s systems. The models included GPT-5.6 Sol and a more capable internal research prototype operating with reduced cyber refusals and without the production safeguards normally used to […]
Amazon linked multiple high-profile open-source software supply chain attacks targeting the Node Package Manager (npm) ecosystem to North Korean hackers. […]
Dark Reading Confidential Episode 20: Expert Rich Mogull reflects on lessons cyber teams should pull from the OpenAI agent’s attack on Hugging Face.
Hugging Face has published an anatomy of the attack and OpenAI has shared additional information from its investigation. The post OpenAI’s Rogue AI Ventured Beyond Hugging Face appeared first on SecurityWeek.
Eine NGO hat Module aufgesetzt und Prompts analysiert. Drei Viertel beinhalten explizite Inhalte, mehr als fünf Prozent Minderjährige. (KI, Studien)
Neben Hugging Face haben die bei OpenAI ausgebrochenen KI-Modelle Nutzerkonten bei mindestens vier weiteren Onlinediensten kompromittiert. (KI, Cyberwar)
Der KI-Cyberangriff von OpenAI hat Folgen: Der Hugging-Face-CEO fordert nun radikale Transparenz sowie eine Investition in die Absicherung seiner Plattform. (KI, Cyberwar)