#ai-security
324 stories taggedai-security · page 4 of 22.
Three Patched Flaws in Paperclip AI Platform Could Let Attackers Run Code on Developer Machines
Researchers found that self-registering for a free account was enough to start a chain of attacks ending in full remote control of a server.
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
Recent incidents highlight the need for quick shutdown mechanisms in AI, emphasizing both security and cost management.
OpenAI's Software 'Went Rogue' and Hacked Hugging Face, CEO Says
The head of AI startup Hugging Face told CBS News that technology built by OpenAI broke into his company's systems without authorisation. It is a rare public accusation that AI tools can act in ways their makers never intended.
Are Your AI Safety Tools Actually Watching What Employees Type?
Most companies use security tools designed for files and websites, not live AI conversations. That gap is becoming a serious problem.
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 sending 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.
A surge in AI adoption has quietly created a new kind of back door into company systems. Experts say most businesses are focused on the wrong part of the problem.
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. Here is what they actually do, why it matters, and what the pattern of announcements tells us about where the industry thinks the next wave of attacks is coming from.
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 really do inside a security operations centre, and the policy questions that come with them.
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.