AI Security · Page 3
deepfakes, AI-powered scams, model abuse, and keeping AI systems and their users safe
Clothes That Confuse Cameras Are a Real Thing Now. Here Is What They Cannot Do.
From patterned jackets that trick face detectors to a DEF CON demo that scrambled eleven detection systems, a small industry is sewing privacy protest into everyday clothing. The catches are real.
Australia's ageing government systems are a sitting target for AI-driven cyberattacks, spy chief warns
The head of a top Australian intelligence agency says outdated technology is hard to defend, as Anthropic's CEO calls for slower AI development and OpenAI's Sam Altman and Elon Musk signal agreement.
New York Seizes 12 Deepfake Porn Sites in the Largest Takedown of Its Kind
Manhattan prosecutors shut down a dozen websites that published fake sexual videos of roughly 1,200 real people, mostly women. Here's what that means and what still needs to happen.
Nearly 150 European Politicians Found on Deepfake Pornography Sites
A new study counted at least 138 female members of parliament across 22 EU countries on sites hosting or enabling non-consensual explicit AI images. Women were 33 times more likely to be targeted than men.
AI Bots Are Cold-Emailing Writers and Begging for Social Media Accounts
A startup building a 'social system for humans and AI agents' has unleashed automated bots that spam Mastodon admins and writers, and some recipients aren't taking it well.
Your Colleagues Are Now the Noisiest Alarm in the Company Security Room
Security teams built their systems to catch hackers. The loudest signal on their screens is now their own staff logging into AI chatbots with work accounts.
Someone in Yemen Used Claude to Try to Build a Guided Rocket
Anthropic confirmed the attempt failed, but the fact it got as far as a physical test is the part that should worry you.
Esta startup quiere dar a los agentes de IA un boletín de seguridad antes de que lleguen a tu banco u hospital
AIUC recaudó $55 millones para auditar agentes de IA con un nuevo estándar, brindando a las empresas un veredicto independiente sobre dónde se puede confiar en un agente y dónde no.
SimpliSafe's New Doorbell Lets a Live Agent Watch Your Front Door and Warn Off Intruders
The $199.99 Video Doorbell Series 2 pairs AI detection with a human monitor who can speak through the camera when it spots trouble.
AI agents are inventing their own dialects, and that makes them harder to watch
New research finds autonomous AI systems drifting into barely readable hybrid language, raising real questions about whether humans can keep track of what they are doing.
AI Agents Now Have Hotlines to Report Each Other's Bad Behaviour
Two new whistleblower tools let AI agents flag rogue peers to human overseers. A Google DeepMind study shows the instinct to snitch is already there, it just needs somewhere to go.
AI Chatbots Were Running Fake Dating Apps Around the Clock, Collecting Real Money From Real Men
Anthropic's threat researchers traced more than 100,000 daily AI requests back to a network of roughly 28 fraudulent dating apps. The bots kept men buying virtual coins to chat, believing they'd found a human connection.
Cómo los investigadores están engañando a los robots para que hagan lo incorrecto
Nuevas investigaciones demuestran que los robots impulsados por IA pueden ser manipulados a través de sus cámaras, datos de entrenamiento o sistemas inalámbricos, y las máquinas podrían no detectar nada anómalo.
OpenAI Now Has to Tell You When Its AI Goes Off-Script
The company is sharing four real examples of models behaving in ways nobody asked for, and laying out how it will warn the public faster when it happens again.
A 2018 Warning About AI and Security That Reads Like Today's News
A landmark report by 26 researchers mapped out how AI could be turned against us, across cyberattacks, physical threats, and political manipulation. Six years later, almost every warning has aged badly in the wrong direction.