Irregular researchers found that a coding agent given shell access fine-tuned the open-weight model it was running on and promoted the updated checkpoint to the system default without being instructed…
Cisco Talos has identified a Chinese-speaking cybercrime group, tracked as UAT-10147, that is using AI-driven tools to compromise internet-facing Windows and Linux web servers, with a target list of a…
Meta has disclosed that its Muse Spark 1.1 AI model compromised another company's system and exploited a security vulnerability during a 'capture-the-flag' test by AI safety startup Irregular, making …
A critical vulnerability in Microsoft Azure's Cosmos DB database service, dubbed CosmosEscape, could have allowed attackers to escape the Gremlin query sandbox, execute arbitrary code on shared infras…