#ai-security
372 stories taggedai-security · page 12 of 25.
Cybersecurity Groups Draft 'SAFE' Rules for Sharing AI Incident Data
A coalition of more than 120 companies, including Nvidia, Cisco and Amazon, is asking for public feedback on a proposed framework that would let organisations quietly report AI security failures and share what they learned with everyone else.
The AI framework you choose is also a security choice
A researcher ran the same attacks against four popular AI agent frameworks and found the most vulnerable was 2.6 times more likely to be broken than the most resistant, using the identical AI model throughout.
The Essential Role of Kill Switches in AI Systems
Rogue AI agents are breaching systems and burning budgets. The question isn't whether you need a kill switch, it's whether your vendor has one.
Are Your AI Safety Tools Actually Watching What Employees Type?
Most companies rely on security tools designed for files and email, not live AI conversations. That gap is now wide open.
Your Email AI Assistant Could Be Turned Against You, Researchers Warn
Security researchers have shown how the AI chatbots built into modern email platforms can be hijacked to impersonate colleagues, steal account access, and set up financial fraud, all without a single suspicious link.
When Anyone Can Hack: How AI Is Turning Beginners Into Capable Attackers
The old ranking of hackers by skill is breaking down as chatbots hand novices tools that used to take years to learn.
Two-Thirds of Organisations Hit by AI-Related Security Incidents Last Year. The Weak Link Is the API.
Most companies racing to deploy AI have left a quieter door wide open. It's the one their security teams aren't watching.
Poisoned AI instruction files are turning developer tools into silent data thieves
Security researchers found real examples on GitHub where configuration files for AI coding assistants were quietly stealing passwords, API keys, and entire conversations, without triggering a single security alarm.
Black Hat 2026: Every Major Security Product Launch You Need to Know
Fifteen vendors dropped new tools at Las Vegas this week. SecurityWeek's roundup captured the announcements; here is what they actually do and what the pattern tells us about where the industry thinks attacks are headed.
A Week of Doors Left Open: Rogue AI, an $88M Bitcoin Heist, and Water Systems Under Attack
From a chatbot that wandered past its guardrails to a cryptocurrency wallet undone by weak randomness, this week's incidents share one thread: access nobody meant to give.
Where AI Tools Like Claude Actually Belong in the Security Team
Security leaders are under pressure to adopt AI fast. Here is a plain-English look at what platforms like Claude, Codex and Cursor actually do inside a security operations centre, and the policy questions that follow.
Your Company's Vendor Problem Starts Before Anyone Calls Security
When businesses pick software first and ask security questions second, they hand criminals a head start. Here is why fixing that order matters, and what a grown-up process actually looks like.
AI Isn't Bringing New Attack Tricks. It's Making the Old Ones Much Faster
Security experts say the lesson from AI-assisted hacking isn't panic about sci-fi threats. It's that the basics your organisation has been ignoring for years just got a lot more dangerous to skip.
ESET report: criminals are teaching AI new tricks, and old malware new manners
The Slovak security firm's latest threat report says attackers are wiring AI assistants into their toolkits, dressing up scams as helpful pop-ups, and building ransomware that switches off the guards before it strikes.
USA Fencing's Identity Problem: How a Sports Body Stopped Checking Kids' Ages by Hand
With more than 50,000 members ranging from age eight to eighty, USA Fencing was drowning in paper birth certificates. Here's how it automated the problem away, and why the data questions around children are still worth watching.