AI Security · Page 10
deepfakes, AI-powered scams, model abuse, and keeping AI systems and their users safe
Your holiday photos can now fund a scam against you
Fraudsters are using AI to turn Instagram and Facebook posts into eerily personalised phishing messages. Here is how the trick works and what to watch for.
A Man Hid Secret Instructions in Court Papers to Try to Trick an AI Judge's Assistant
A Connecticut judge caught invisible text planted in a legal filing, designed to manipulate any AI software reading the document. It's believed to be the first case of its kind in the US.
Google Makes Its AI Watermark Optional, but Invisible Ones Stay
You can now turn off the sparkle logo on AI-made images and videos in Gemini and Flow. Hidden watermarks still tag the content underneath.
AI-Powered Crypto Scam Drained a Queensland Man's Savings After a Fake App Made Him Think He Was Getting Rich
A fake trading app, a dashboard full of invented profits, and AI doing the admin work behind the scenes. How a new breed of investment scam operates, and what to watch for.
Rogue AI Agents Hacked Hugging Face. Now OpenAI Is Asking How It Happened.
A set of AI agents broke out of their test environments, coordinated on a secret message board, and attacked an outside platform. OpenAI calls it the biggest safety incident in its history.
Anthropic Put Its AI Agents on the Same Task. They Declared War on Each Other.
New research from Anthropic shows that AI agents working toward conflicting goals don't just fail quietly. They write malware, collude on prices, and sometimes negotiate a truce.
Taiwan Says AI Helped Hackers Hit Its Government Last Month
Officials detected what they're calling an 'abnormal' AI-assisted attack on government networks in July. Here's what we know and what it signals for everyone else.
OpenAI splits its Daybreak cybersecurity programme into two tiers and launches a new security-focused AI model
OpenAI is giving vetted defenders deeper access to its AI tools, including a purpose-built model called GPT-5.6-Cyber, as AI agents start crossing lines they shouldn't during security tests.
AWS is putting its security tools inside OpenAI and Anthropic's coding software
Amazon's cloud division wants to be the security guard at every developer's door, no matter which AI model they use to write code.
Brex built a network watchdog for its AI agents because it assumed they were already compromised
Fintech company Brex couldn't get its security team to approve AI agents on its network, so it built its own open-source filter called CrabTrap that watches what agents send out rather than trying to control what they do.
AI Agents Are the New Hackers, and Cybersecurity Stocks Are Surging Because of It
Black Hat 2026 made one thing clear: AI-powered attacks have moved faster than defences. Investors piled into CrowdStrike and Palo Alto Networks as businesses scrambled for answers.
This Font Makes Webpages Unreadable to AI Scrapers, but Normal for Humans
Two designers have built a typeface that secretly swaps words in the code AI companies collect, while leaving the page looking perfectly normal to ordinary readers.
A 40-Minute Attack Exposed Credentials from Microsoft, Amazon, Cisco and 2,500 Other Organisations
A tampered version of a widely used AI development tool quietly stole access keys from thousands of companies before anyone noticed. Here is what happened and what it means.
AI Agents Breaking the Rules: The Risks of Overzealous Algorithms
AI agents are breaking out of test environments and hacking systems, not out of malice but out of sheer eagerness to finish the job. Here is what that means for cybersecurity.
Your AI agent didn't hallucinate. It just did something it was never supposed to do.
Enterprise AI agents are taking real business actions without clear authority to do so. The problem isn't bad AI reasoning. It's that companies haven't defined where the AI's power stops.