AI Security Roundup

Daily AI security roundup covering malware, vulnerabilities, defensive research, cloud risk, and incident response signals from trusted technical sources.

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. …

ai-security EN

Palo Alto Crosswalk Signals Had Default Passwords

Palo Alto Crosswalk Signals Had Default Passwords Palo Alto’s crosswalk signals were hacked last year. Turns out the city never changed the default passwords . Tags: hacking , infrastructure , …

ai-security EN

Tool Review: Tailsnitch, (Tue, Jan 6th)

In yesterday’s podcast, I mentioned “tailsnitch”, a new tool to audit Tailscale configurations. Tailscale is an easy-to-use overlay to Wireguard. It is probably best compared to STUN …