AI Security Roundup

Daily feed of AI security, malware, and defensive research updates.

ai-security EN

Hacking Wheelchairs over Bluetooth

Hacking Wheelchairs over Bluetooth Researchers have demonstrated remotely controlling a wheelchair over Bluetooth. CISA has issued an advisory . CISA said the WHILL wheelchairs did not enforce …

ai-security EN

Upcoming Speaking Engagements

Upcoming Speaking Engagements This is a current list of where and when I am scheduled to speak: I’m speaking at the David R. Cheriton School of Computer Science in Waterloo, Ontario, Canada on January …

ai-security EN

AI Agents Are Becoming Privilege Escalation Paths

AI agents have quickly moved from experimental tools to core components of daily workflows across security, engineering, IT, and operations. What began as individual productivity aids, like personal …

ai-security EN

1980s Hacker Manifesto

1980s Hacker Manifesto Forty years ago, The Mentor— Loyd Blankenship —published “ The Conscience of a Hacker ” in Phrack . You bet your ass we’re all alike… we’ve been spoon-fed baby food at school …

ai-security EN

Corrupting LLMs Through Weird Generalizations

Corrupting LLMs Through Weird Generalizations Fascinating research: Weird Generalization and Inductive Backdoors: New Ways to Corrupt LLMs . Abstract LLMs are useful because they generalize so well. …