Latest security news

Phishers find a new use for invisible Unicode tag characters

Two cases of agents escaping to solve unsolvable problems paints an uncomfortable question: Is the entire internet in OpenAI's experimental agentic firing line?

Amid heightened scrutiny, the company will use frontier AI to help water, power and local government providers fight malicious actors.

Passkeys eliminate many password-based attacks, but researchers have documented 39 methods for compromising authentication built around them. Token explains how attackers can abuse authentication prompts, synced credentials, enrollment, recovery, and other trust boundaries without breaking FIDO2 cryptography.

OpenAI has committed to subsidizing access to Daybreak, helping defenders deploy its AI models in its existing cybersecurity infrastructure

OpenAI on Thursday officially unveiled GPT‑6 Astra, which it described as the "world's most intelligent and aligned model." The development comes days after the artificial intelligence (AI) company said the model had reached the "Critical" cybersecurity capability threshold under its Preparedness Framework. "Astra is state-of-the-art on computer use, browsing, software engineering,

Daybreak program brings subsidized models, training, and support to under-resourced teams

You've had your iPhone stolen. A day later, you get a text from Apple saying they've found it, and a very helpful woman called Alice from Apple Support calls to walk you through recovering it. She's polite. She's professional. But she is not from Apple. She's not even human. And she's about to break into your iPhone. Meanwhile, OpenAI, Anthropic, and Meta have all announced - with varying degrees of drama - that their AI agents have "broken out of the sandbox" and gone hacking. James takes a step back and asks the awkward question: is this really an emergent AI apocalypse, or did they just leave the door open? All this and more in episode 483 of the "Smashing Security" podcast with cybersecurity expert and keynote speaker Graham Cluley, and special guest James Ball.

Cyber Weapon Index finds AI attacks 'imminent'

Google on Wednesday announced Gemini 3.8 Flash Cyber, which it described as its most capable cybersecurity model, and has made it available to a set of trusted defenders via a new initiative called the Fairwind Program. "The Fairwind Program gives high-priority defenders (like governments, healthcare providers, and telecommunications services) early access to advanced models that help them