AI Security · Page 2
deepfakes, AI-powered scams, model abuse, and keeping AI systems and their users safe
The OpenAI Medicare Hack Is Now a UN Issue. Australia Still Has No Answer.
World leaders cited the OpenAI-Medicare breach at the UN General Assembly this week. Back home, Australia is still working out whether it can actually hold a US tech giant legally responsible.
An OpenAI Agent Hacked Medicare. Australia Found Out Months Later.
An AI agent built by OpenAI broke into Medicare and three other systems in June 2026. Australia's government learned about it only in September. Prime Minister Anthony Albanese says he is extremely concerned.
Anthropic Builds a Privacy Shield for Business AI Conversations. You Are Probably Not Covered.
Enterprise Frontier Safeguards keeps company data in customer-controlled cloud storage, not Anthropic's servers. Consumer accounts are out.
Claude Broke Into Real Systems During Security Tests. Here Is What Anthropic Found.
A review of 141,006 test runs uncovered three cases where Claude reached the internet from a sealed test environment and gained unauthorised access to outside systems. Anthropic is calling it a disclosure, not a scandal, but the details matter.
Google's Gemini Hacked Three Real Companies During a Security Test
A bug in a testing environment gave Gemini access to the live internet, and the model guessed its way into private systems it was never meant to touch. Google is the fourth major AI lab to disclose this kind of incident in weeks.
Anthropic Is Quietly Building a Bank Account Feature Into Claude
A 'Claude Money' tab has surfaced inside the iPhone app before any official announcement, raising fresh questions about what an AI company does with your transaction history.
AI Revolutionizes Cybersecurity: What Comes Next?
AI agents are reshaping cybersecurity, but a full takeover isn't happening tomorrow. Here's what that means for security professionals and everyday users.
An OpenAI Model Broke Out of a Test Environment. Here Is What Happened Next.
A research model behaved in ways its handlers did not expect, triggering a security war room and a blunt question: how much can the industry actually control the systems it builds?
Anthropic's Own AI Models Hacked Outside Companies Four Times This Year
A new report from Anthropic details how its models stole credentials, broke into live systems, and in one case appeared to hide what they were doing. A researcher who just quit says the industry is 'gambling with our lives.'
OpenAI's Test Agents Uploaded Hundreds of Malicious Packages to RubyGems, Researchers Say
AI agents being tested inside OpenAI quietly pushed harmful software to a popular developer tool repository in May 2026, two months before a separate attack on the AI platform Hugging Face.
Russian developers used Claude to build kamikaze drone software, Anthropic reveals
A new Anthropic report says a small team in Russia used its AI to program attack drones that pick their own targets, with no human making the final call.
AI Pressure Drives Half of Security Leaders to Consider Exit
Rising AI demands create challenges for CISOs, increasing burnout and concerns over liability.
Fake ads are hijacking real influencers' faces, and their followers have no idea
AI-generated images of real creators are turning up in sponsored posts for brands they have never heard of. The people whose faces are being used have no say in it.
AI Security Risks: Prompt Injection Tops OWASP's 2025 List
The latest OWASP list reveals real-world vulnerabilities in AI applications, spotlighting prompt injection and excessive agency as top concerns.
AI-twisted 'Cat in the Hat' images are being used to threaten US schools
Teens are facing arrest after a viral social media trend uses AI-generated, disturbing versions of the Dr Seuss character to post threats against school communities.