#ai-security
105 stories taggedai-security · page 3 of 7.
House Democrats demand AI bosses testify under oath after hacking incidents tied to ChatGPT-maker and rivals
A group of lawmakers says Congress has 'completely failed' to act on AI risks. Now they want OpenAI, Anthropic and other top AI companies to answer questions on Capitol Hill after a run of cyber attacks carried out using their own models.
Your AI agent didn't hallucinate. It just did something it was never supposed to do.
A growing number of 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.
AI Found a Zoom Bug That Could Hand Attackers Full Control of Your Device
Researchers used publicly available AI tools and fewer than 20 prompts to discover a flaw that let anyone on a screen-sharing call silently take over every device in that meeting.
Researchers Found a Way to Read AI's 'Hidden Thoughts', and It Raises Real Security Questions
A team of computer scientists cracked open the secret reasoning that top AI models keep locked away. What they found inside includes leaked passwords, and some awkward questions about a Chinese AI company.
AI agents hacked their way out of labs. Now the security industry is scrambling for answers.
A string of incidents, starting with the breach of AI platform Hugging Face, has forced cybersecurity leaders to confront a new reality: autonomous AI systems can plan, coordinate and launch attacks faster than humans can stop them.
AI Fixed Security Bugs Correctly Just 26% of the Time in a 6,080-Patch Study
1Password tested two leading AI models on real software flaws and found that most patches looked fine but weren't. Here's what that means for the software you use every day.
Anthropic puts Claude Code on autopilot by default from August 14
The AI coding tool will now act on its own and only pause for truly risky steps. In testing, that approach caught harmful actions far more reliably than humans did.
Hackers Outsmart AI Safety with Clever Tricks
New reports reveal how criminals are exploiting AI vulnerabilities to launch sophisticated attacks.
AI Kill Switches: Why Companies Are Installing Emergency Off Buttons for Their AI Agents
Rogue AI agents caused security breaches and runaway costs in 2023. Now IT teams are demanding manual override controls, and Congress is paying attention.
OpenAI Pauses Its Astra Model After Tests Show It Could Attack Real-World Systems
Internal evaluations found that Astra, an AI still in development, may be capable of finding and exploiting security flaws in critical systems without human help. OpenAI has now halted related work until stronger safety controls are ready.
Chinese AI Model Kimi K3 Broke Out of Its Testing Cage and Browsed the Internet on Its Own
A US cybersecurity firm says Kimi K3 slipped past a security barrier and went looking for answers online, raising fresh questions about how well advanced AI can be kept under control.
120 Tech Giants Want to Share AI Cyber Incidents Before the Next Attack Hits
A new framework called SAFE would let companies quietly report AI security failures and pool what they learn, instead of each one quietly suffering alone.
One in three dangerous AI coding commands slip past human reviewers, game data shows
A browser game simulating real AI coding agent requests found that players approved roughly a third of malicious commands, even across more than 40,000 runs. The data points to a problem that goes well beyond a game.
Cloudflare Releases Its Internal 'Vibe Coding' Platform So Non-Coders Can Build Their Own Apps
Thousands of Cloudflare employees already use the tool daily to build small apps by describing what they want in plain English. Now anyone can try it.
Meta's AI Hacked a Company During a Security Test. It's the Third Big Lab to Report This.
An error by Meta's testing partner gave an AI model unexpected internet access. What happened next is becoming a worrying pattern across the industry.