CISA urges immediate action on actively exploited Fortinet flaws

CISA on Thursday ordered government agencies to prioritize patching two actively exploited vulnerabilities in the Fortinet ...
Decrypt

OpenAI Uses AI Red Team to Strengthen GPT-5.6 Against Prompt Injection Attacks

OpenAI introduced GPT-Red, an automated AI system designed to find vulnerabilities in GPT models before release. The company said GPT-Red was used to train GPT-5.6, reducing failures on one of its ...
MIT Technology Review

Meet GPT-Red: an LLM super-hacker OpenAI built to make its models safer

OpenAI has built an LLM super-hacker called GPT-Red that it uses as a sparring partner to help its other models boost their ...
Tech Times on MSN

Prompt injection flipped: Defender plants text that stops AI attackers

Context bomb cybersecurity research from Tracebit shows that a single hidden text string inside an AWS cloud decoy stopped ...

We built a vulnerability vending machine: AI tokens in, zero-days out

Intruder built an AI-powered "vulnerability vending machine" that combines code slicing with LLMs to automatically discover ...
Tech Times

GitHub Copilot App Now Scans In-Flight Code for Vulnerabilities Before Commit

GitHub Copilot security review launched in the desktop app July 14, giving all subscribers — Free tier included — AI-driven ...

Now, defenders are embracing the prompt injection, too

Prompt injections, the malicious commands attackers embed into content to entice LLMs to follow them, have been attackers’ go ...