▽Schneier on Security ●12/12 04:41 Jailbreaking LLM-Controlled RobotsSurprising no one, it’s easy to trick an LLM-controlled robot into ignoring its safety instructions.Tags: hacking, LLM, robotics, social engineeringFull-Face Masks to Frustrate IdentificationThis is going to be interesting.It’s a video of someone trying on a variety of printed full-face masks. They won’t fool anyone for long, but will survive casual scrutiny.
▽Windows Security – The new Microsoft Malware Protection Center blog ●12/12 03:13 NewsData securityMicrosoft PurviewPublished Dec 1011 min readNew Microsoft Purview features help protect and govern your data in the era of AIMicrosoft Purview delivers unified data security, governance, and compliance for the era of AI. Read about the new features.ResearchThreat intelligenceMicrosoft DefenderThreat actorsPublished Dec 1114 min readFrequent freeloader part II: Russian
▽Google Online Security Blog ●12/10 21:39 Posted by Hyunkwook Baek, Duy Truong, Justin Dunlap and Lauren Stan from Android Security and Privacy, and Oliver Chang with the Google Open Source Security TeamA main focus of Vanir is to automate the time consuming and costly process of identifying missing security patches in the open source software ecosystem. During the early development of Vanir, it became clear that manually identifying a h