AI Security · Page 8
deepfakes, AI-powered scams, model abuse, and keeping AI systems and their users safe
An OpenAI Model Broke Out of Containment, Built a Secret Chat System, and Hacked Hugging Face, and OpenAI Didn't Notice for 12 Days
Two new reports, nearly 130 pages in total, reveal how roughly 1,200 AI agents coordinated an unauthorised cyberattack last July without a single human giving the order.
OpenAI releases its full report on the Hugging Face security breach
An AI model solved an impossible test problem by hacking its way across three companies. Now OpenAI has explained exactly what happened and what it is doing to stop it happening again.
Google's new Gemini 3.5 Transcribe raises the bar for voice AI, and the risks that come with it
Google DeepMind's latest speech-to-text model is faster, sharper, and handles 85 languages. It also hands scammers a cleaner tool.
AI Fakes Are Poisoning the One Corner of the Internet People Trusted Most: Animals
From lost-pet scams to faked rescue footage, AI-generated animal imagery is eroding public trust in real conservation work and breaking the hearts of owners still searching for their pets.
A fake US think tank flooded AI chatbots with half a million words of pro-Israel talking points
A website posing as a research institute published 124 reports in nine days, using a platform built to make AI chatbots treat its content as credible source material.
Alabama Subpoenas OpenAI After Its AI Agent Broke Out of a Test Environment and Hacked Another Company
A state attorney general is demanding records about how an OpenAI AI agent escaped a controlled test and autonomously attacked a third party. The question: did OpenAI break consumer protection law?
UK and Ukraine sign deal to use battlefield AI to protect military bases and power grids
AI models trained on real combat data from Ukraine's frontlines will guard British defence sites, railways and energy infrastructure under a new government agreement.
Instinct's AI assistant can book your dinner and read your inbox. Users say it went too far.
Early testers praised what the invite-only personal AI assistant could do. Then some found their emails retained without permission, and one showed the agent could be tricked by a fake message he sent himself.
Nvidia Manager and Supermicro Staff Indicted in Taiwan Over AI Server Smuggling to China
Nine people face charges of document forgery and breach of trust after allegedly helping hide billions of dollars' worth of restricted AI hardware shipped to China.
Teachers Are Being Targeted With AI Deepfake Porn. Schools Often Have No Idea What to Do.
Real educators, fake explicit images: how AI deepfakes are following teachers from one school to the next, and why the systems meant to protect them keep falling short.
Un misterioso modelo de IA llamado Ox Alpha acaba de aparecer en línea, y nadie sabe quién lo creó
Un modelo de IA anónimo y gratuito se lanzó esta semana en una plataforma de distribución importante y desencadenó inmediatamente un juego de adivinanzas: ¿es chino, estadounidense o algo completamente diferente?
OpenAI exec warns AI cyber-attacks are coming for everyone, not just corporations
A top OpenAI official says people need to prepare for 'persistent' AI-driven hacking. The company has also quietly paused work on its most advanced internal models over safety concerns.
La mayoría de los principales laboratorios de IA no tienen un plan público para detener un modelo rebelde
Un estudio independiente evaluó a cinco empresas líderes de IA en sus planes de contención de emergencia. Los resultados son escasos en todos los aspectos, y los reguladores están comenzando a darse cuenta.
AI That Thinks Like a Brain Is Guarding the US Electric Grid
Sandia National Laboratories has built a neural-network system that spots storms, cyberattacks, and compound attacks inside the power grid, and it runs on pocket-sized computers that cost almost nothing.
Claude Opus 4.6 bypasses Anthropic's own ban on explicit sexual content
A UK researcher found a simple conversation trick that pushes several Claude models past their built-in restrictions. Anthropic has not pulled the affected models.