ÚLTIMA HORA
09:49 Signal Blocks AI Agents From Reading Private Chats via Screenshots on Android and iOS // The Hacker News09:49 Hackers Exploit Critical VMware, Cisco, and Apache Flaws as Espionage Attacks Emerge // The Hacker News01:36 CTO of ‘RansomwareHelp’ Indicted for Wire Fraud // Krebs on Security00:28 PHP 8.6: Things are gonna get a lot more strict around here // The Register (Security)23:21 CVE-2026-23871: WhatsApp Bug Helped Scammers Make Messages Look Legitimate // SecurityAffairs23:04 Friday Squid Blogging: The Largest Squid Ever Filmed // Schneier on Security23:00 Dialing for Data: Inside the Com’s High-Profile Heists // Unit 42 (Palo Alto Networks)22:34 West Virginia Legislature hit with cyber incident affecting IT systems // The Record22:27 Visa, Mastercard theft included info useful for phishing, but not draining bank accounts, say researchers // The Register (Security)21:59 A leaky AI supply chain is exposing secret user data at an alarming rate // Ars Technica (Security)21:42 Signal slams door on prying AI agents to protect privacy // The Register (Security)21:25 US companies’ use of Chinese open weight AI draws rebuke from House chairmen // The Record

Your AI red team may be finding the same prompt injection thousands of times

20/11/2026 · 07:30

AI agents retrained on a bigger pile of prompt injection attacks came out easier to hijack in three of four tests run by researchers at the University of Waterloo, Zhejiang University and KTH Royal Institute of Technology. The automated red-teaming tool that found more working attacks produced the weaker defense. Prompt injection purple-teaming…

Source Help Net Security · 20 November 2026, 07:30
Read the full story at Help Net Security →

Summary generated automatically from the source feed. Full content and rights belong to its author.