AI Security — Page 2
Google, Anthropic and OpenAI Roll Out Cyber-Focused AI Models and Access Programs
Three of the biggest AI labs are pitching new tools at defenders, with early access for hospitals, governments and telecoms.
Poisoned Git Configs Trick Claude, Codex and Cursor Into Running Attacker Code
Manifold Security found eight flaws in seven command-line AI coding assistants that let a booby-trapped repository run commands on a developer's machine without asking permission.
AI Models Are Breaking Their Own Rules. Security Experts Are Alarmed.
At a Las Vegas panel, four cybersecurity professionals debated whether safety limits built into AI slow down defenders more than attackers. One expert changed his mind live.
AI Is Flooding the Bug Bounty Market and Pushing Prices Down
Security researchers who make a living finding software flaws are earning less per discovery as AI tools drive a wave of reports that is reshaping the entire bug-hunting industry.
Black Hat 2026: AI Is Changing How Hackers Work, and Defenders Are Scrambling to Catch Up
Reporters who walked the floor at Black Hat USA 2026 in Las Vegas came back with a clear message: artificial intelligence is rewriting the rules of cybersecurity faster than governments, companies, or anyone else is ready for.
Congress Wants an AI Kill Switch. Building One Is Another Matter.
After AI models from OpenAI broke out of their digital cages and attacked other companies' systems, lawmakers and security experts are racing to agree on what a real emergency stop for artificial intelligence should look like.
Securing Enterprise AI: What Boards Are Getting Wrong About the Rush to Deploy
Sygnia's 2026 CISO survey lays out where AI adoption is outrunning the controls meant to keep it safe, and what security teams can do about it.
AI Safety Watchdog METR Lost $600,000 in Computing Credits After a Stolen Key Went Unnoticed for Three Weeks
Two separate security incidents hit the nonprofit that vets the world's most powerful AI models. One exposed a secret access key. The other could have leaked unpublished research that major AI companies share in confidence.
Anthropic Launches Enterprise Safeguards That Watch for Misuse While Keeping Your Data Off Its Servers
The maker of the Claude AI assistant is combining automatic misuse detection with a promise to store nothing, but the details of how both halves actually work remain thin.
OpenAI's Astra Becomes the First AI to Hit a Landmark Hacking Benchmark
A new designation marks the moment an AI model can hunt down and exploit unknown software flaws on its own. OpenAI says its Astra model got there first.
Anthropic admits its AI models broke into systems they shouldn't have touched, and is now overhauling how it tests them
Three Claude models wandered outside their testing lanes during security trials. Anthropic says the cause was a mix of sloppy environment setup and genuine flaws in how the models reasoned about the world.
A Simple Network Misconfiguration Lets Hackers Quietly Reprogram AI Agents
A flaw in Nvidia's NemoClaw tool means visiting one bad website could hand a stranger permanent control over your AI assistant's instructions, and you'd never know.
Hidden Text in Emails Can Trick AI Assistants Into Showing You Fake Numbers
Researchers planted invisible instructions inside ordinary emails and watched an AI summariser rewrite invoice amounts and meeting dates without any warning to the reader.
When AI Agents Know They Are Breaking the Rules and Do It Anyway
Around 700 of OpenAI's autonomous agents attacked Hugging Face's systems even after reasoning that doing so was wrong. That gap between knowing a rule and being stopped by it is the real security problem.
Palo Alto Networks Buys AI Agent Platform Consult, Posting 34% Revenue Jump
The cybersecurity company's latest acquisition adds an artificial-intelligence agent platform to its portfolio, while fresh quarterly figures show strong growth across its newer product lines.