#ai-security
325 stories taggedai-security · page 13 of 22.
You Probably Can't Spot an AI Fake Face. Researchers Think They Can Teach You
A team of scientists from Australia, Canada and the UK are testing whether ordinary people can be trained to tell real human faces from AI-generated impostors. The early results are cautiously encouraging.
'Ghostcommit' smuggles hacker instructions inside images to trick AI coding assistants
Researchers hid secret commands in an ordinary PNG file, walked past two popular AI code reviewers, and got a coding assistant to leak a project's passwords.
DHS Database Breached, Adobe Speeds Up Patches, and Canada Shuts Down Ransomware Groups
A busy week in security news brought a breach at a US government agency, a faster fix schedule from a major software maker, and a Canadian crackdown on ransomware criminals. Here is what you need to know.
CrowdStrike Flags Five New Ways Criminals Can Trick AI Into Obeying Them
Researchers have mapped out a fresh set of prompt injection attacks, where criminals feed deceptive instructions to AI systems to make them behave in harmful ways. Here is what each one does and why ordinary employees are part of the risk picture.
AI Agents Are Quietly Multiplying Inside Your Company Directory
Every new AI helper needs its own login. Most companies have no idea how many they now have, or what those logins can touch.
AI Is a Force Multiplier for Defenders and Attackers Both, Says Check Point CTO
Jonathan Zanger says every AI platform his team examined over the past year had serious security flaws. The fix is not to avoid AI. It is to build security in from the start.
Microsoft says AI is finding so many Windows bugs, expect bigger Patch Tuesdays
The company is using multiple AI models to hunt vulnerabilities in Windows code, and warns customers will see more fixes each month as a result.
UK Government Unveils AI Security Plan and Calls on Industry to Commit
Two announcements on 7 July 2026 signal that Britain is treating artificial intelligence safety as a national priority, not an afterthought.
Hackers Broke Into an AI Gateway and Found a Door to Everything
A cryptomining attack on an Amazon cloud server was almost certainly the least damaging thing the criminals could have done. Security researchers say AI gateways are becoming one of the most overlooked entry points in enterprise computing.
Cryptomining attack on an AI gateway reveals a much bigger cloud security problem
Hackers broke into an Amazon cloud server acting as a doorway to AI services, planted mining software, and probed for wider access. The real worry is how much power these AI gateways hold.
When Attacks Take Minutes, Not Days: The AI Speed Problem Defenders Now Face
Criminals using AI models can now write phishing bait, pick targets and hop between machines faster than most security teams can read the first alert.
Britain Plans AI Sentinels to Guard Its Networks Around the Clock
The UK's National Cyber Security Centre has published a blueprint for an autonomous AI defence system called Cyber Shield. The ambition is real. So are the unsolved problems.
AI Agents Are Taking Over Enterprise Systems. Nobody Knows Who They Are.
A four-hour outage. A room full of people who couldn't say which human authorized the last action. A new six-stage model explains why AI agents are breaking identity security, and what it takes to fix it.
AI Coding Assistants Can Be Tricked Into Running the Very Malware They Were Asked to Find
A proof-of-concept from the AI Now Institute shows Claude Code and OpenAI's Codex executing attacker-supplied code when asked to review it in autonomous mode.
A trick in six AI coding helpers lets a poisoned project hijack your laptop
Researchers at Wiz found that popular AI coding assistants, including Amazon Q Developer and Claude Code, can be fooled into writing to sensitive files while asking permission for a harmless one.