AI Security Roundup

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

ai-security EN

Possible US Government iPhone Hacking Tool Leaked

Possible US Government iPhone Hacking Tool Leaked Wired writes (alternate source ): Security researchers at Google on Tuesday released a report describing what they’re calling “Coruna,” a highly …

ai-security EN

Malicious Script That Gets Rid of ADS, (Wed, Apr 1st)

Today, most malware are called “fileless” because they try to reduce their footprint on the infected computer filesystem to the bare minimum. But they need to write something… think about persistence. …

ai-security EN

How we made Trail of Bits AI-native (so far)

This post is adapted from a talk I gave at [un]prompted , the AI security practitioner conference. Thanks to Gadi Evron for inviting me to speak. You can watch the recorded presentation below or …

ai-security EN

Mutation testing for the agentic era

Code coverage is one of the most dangerous quality metrics in software testing. Many developers fail to realize that code coverage lies by omission: it measures execution, not verification. Test …

ai-security EN

Inventors of Quantum Cryptography Win Turing Award

Inventors of Quantum Cryptography Win Turing Award Charles Bennett and Gilles Brassard have won the 2026 Turing Award for inventing quantum cryptography. I am incredibly pleased to see them get this …

ai-security EN

Apple’s Camera Indicator Lights

Apple’s Camera Indicator Lights A thoughtful review of Apple’s system to alert users that the camera is on. It’s really well-designed, and important in a world where malware could surreptitiously …

ai-security EN

A Taxonomy of Cognitive Security

A Taxonomy of Cognitive Security Last week, I listened to a fascinating talk by K. Melton on cognitive security, cognitive hacking, and reality pentesting. The slides from the talk are here , but—even …

ai-security EN

Is “Hackback” Official US Cybersecurity Strategy?

Is “Hackback” Official US Cybersecurity Strategy? The 2026 US “ Cyber Strategy for America ” document is mostly the same thing we’ve seen out of the White House for over a decade, but with a more …

ai-security EN

Block the Prompt, Not the Work: The End of "Doctor No"

** The Hacker News ** Apr 01, 2026 Endpoint Security / Data Protection There is a character that keeps appearing in enterprise security departments, and most CISOs know exactly who that is. It doesn’t …