Red, an in-house AI hacker that attacks its own models to harden GPT-5.6 against prompt injection, and it works too well to release.

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 ...

Gwen Shapira shares how teams are scaling AI features using PostgreSQL for mission-critical apps. She explains how to ...

Recent incidents show attackers moving beyond LLM-written phishing lures to using AI across attack chains. Security teams ...

From a rushed ShareFile shutdown to poisoned npm packages and AI assistants tricked into installing malware, here's every ...

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

Cybercriminals are cloning trusted news websites using AI-generated content to promote fake investment schemes, making it harder than ever to distinguish legitimate journalism from scams.

AI-native web browsers make it easier to get information and perform tasks online, but they also come with more security ...

With the ability to take control of distributed devices at scale, HalluSquatting has the potential to achieve various ...

A practitioner's breakdown of the CSRF attack: how the forged request works, two documented exploits, a manual test, and the ...

A cybersecurity researcher revealed this week that Anthropic's Claude artificial intelligence assisted him in discovering a ...

A researcher found that using Anthropic’s Claude Opus 4.7, he could break into the website of Front Gate—used by every ...