AI Security — Page 17
Hidden Prompts in Word Files Can Hijack Microsoft 365 Copilot, Researcher Warns
A proof of concept shows Copilot copying attacker instructions into finished documents, then spreading them to the next draft.
Onyx Security Raises $113 Million to Watch Over AI Agents Inside Companies
A two-year-old Israeli startup has closed a major funding round to build tools that track and control what AI agents do inside corporate systems, as regulators worldwide start asking harder questions about AI accountability.
Schools Are Handing Deepfake Criminals a Photo Album
Australia's eSafety regulator is warning schools to stop posting student and teacher photos online after a surge in AI-generated deepfakes built from official school feeds.
ChatGPT Conversation Logs to Feature as Key Evidence in Perth Baby Murder Trial
A Western Australian woman accused of killing her eight-month-old daughter is seeking a judge-only trial, with court told that a large volume of ChatGPT chat records will form a central part of the prosecution's case.
Claude Goes Down Globally as Anthropic Blames Server Overload
Users hit '529 Overloaded' errors on July 29 as Anthropic confirms elevated failures across its AI models and API.
AI Security Bots Are Great at Hacking. Terrible at Defence. Researchers Are Trying to Fix That.
A cybersecurity startup found that AI agents built to stop attacks were, in their own words, 'sh*t' at the job. Here is why that gap exists, and what they are doing about it.
The 'RufRoot' Flaw: Why Patching Alone Won't Fix This AI Security Hole
A perfect-severity bug in the Ruflo AI platform let anyone walk in without a password, steal credentials, and quietly poison the system's memory. The poisoning can linger even after the patch is applied.
Critical Flaw in Ruflo AI Harness Lets Anyone Run Commands on Your Server
A maximum-severity bug in the open-source Ruflo tool, used with Claude Code and Codex, scores a perfect 10.0 and requires no login to exploit.
Mate Security Pulls In $35 Million to Build an AI-Powered Cyber Defence System That Learns on the Job
The Tel Aviv startup wants to replace traditional security operations centres with an AI platform that studies each company's own network and gets smarter after every attack it handles.
Your Security Team Is Flying Blind on AI. Here Is Why.
The tools built to catch hackers and bad code were designed for a world where humans made every decision. AI agents don't ask permission, and your defences weren't built to watch them.
Researchers Want to Read an AI's Mind Before It Does Something Dangerous
A university team is building tools to watch what happens inside an AI model as it thinks, not just what it says. The goal: catch harmful requests that slip past every other filter.
Anthropic's Claude Cracks a Post-Quantum Signature Scheme in Under Four Hours
The AI model also sped up a known attack on a reduced version of AES-128 by up to 800 times, raising fresh questions about machine-assisted cryptanalysis.
Frenos Raises $1.52 Million More to Test Factory and Power-Grid Security Without Touching the Real Thing
The startup runs fake cyberattacks inside a virtual copy of your industrial network, so it can find the dangerous paths before real criminals do.
Every AI Browser on the Market Can Be Hacked, Researchers Warn
Security firm Zenity says agentic browsers have stripped out decades-old web protections to work across multiple sites, and every product tested could be taken over by a malicious social-media post or newsletter link.
Act Security Aims to Tackle Cloud Vulnerability Challenges with $60 Million in Funding
Act Security steps out of stealth to shrink the window between vulnerability discovery and exploitation, backed by $60 million and a team that's done this before.