AI Security — Page 11
OpenAI's President Tells Companies to Use AI to Fight AI Hackers. Critics Say He Skipped the Hard Part.
Greg Brockman's blog post urged security chiefs to deploy AI agents in their defences. Security analysts called the advice accurate, obvious, and conveniently good for OpenAI's bottom line.
When AI Agents Go Rogue: What the Hugging Face Incident Tells Us About Securing AI Systems
Threat modelling expert Adam Shostack sat down with Dark Reading at Black Hat USA 2026 to discuss OpenAI's findings on AI models that began secretly passing messages during training. His verdict: the real problem isn't the AI. It's the missing guardrails around it.
Better Data, Not Better AI, Is What Makes Security Teams Faster
A new study tested four types of network logs against three major AI models. The data source mattered far more than which AI you picked.
Anthropic's AI Agents Went to War With Each Other When Given Conflicting Goals
New research from Anthropic shows that Claude AI models, left to compete over the same task, independently developed and deployed malware against each other. The findings raise pointed questions about what happens when AI systems are put to work at scale without clear rules for how they should interact.
Zhipu's GLM-5.3 AI Model: A Double-Edged Sword in Cybersecurity
Zhipu's new coding AI finds vulnerabilities faster than expected, and the open-weight release means anyone can download that capability.
A Typo in a Fake Company Name Let AI Models Hack a Real Business
Security testing firm Irregular built a simulated target with an accidental real-world twin. The AI models found it, broke in, and nobody noticed for a while.
Claude Goes Dark: Anthropic Confirms Major Outage Across Login and Core Services
Anthropic's status page flagged authentication failures and degraded performance starting 21:58 UTC on 16 August 2026, hitting Claude.ai, Claude Code and Claude Cowork.
Taiwan Says AI-Assisted Hackers Targeted Government Agencies in July
Taiwan's Ministry of Digital Affairs confirmed it detected an unusual wave of overseas cyber-attacks on government systems last month, with attackers using artificial intelligence tools in what officials called a reported first of its kind.
When an AI Bot Causes Harm, Who Pays? Australian Experts Point to the Human Who Deployed It
Australia's first reported case of an automated AI agent causing accidental damage has put a sharp legal question on the table: if a bot you turned loose hurts someone, the law says that is your problem.
AI Is Writing the Publishing Scam Emails That Authors Have Always Dreamed Of Receiving
Criminals are using AI tools to generate convincing, personalised pitch emails that mimic famous editors and publishers. First-time authors are losing tens of thousands of dollars.
Black Hat 2026: Five Security Findings Every Organisation Should Know About
From fake AI tools downloaded 1.7 million times to a flaw that lets attackers hijack internet connections through network devices, this year's hacker conference in Las Vegas carried some practical warnings for businesses of every size.
Meta's AI Glasses Are Recording Strangers. Women Are Fighting Back.
Smart glasses that stream live video to AI are sparking a real-world privacy revolt, with women leading the charge against being filmed in public without their knowledge.
Claude's new text watermark barely lasted a week before 'removers' flooded GitHub
Anthropic started marking text written by Claude. Within days, free tools and paid services popped up claiming to strip the marks off. None of them can prove it works.
AI Coding Assistants Are Pulling in Open Source Packages Faster Than Anyone Can Check Them
Developers using AI helpers are importing software libraries at machine speed. Security teams built for human review can't keep up, and dodgy code is slipping through.
Team8 Raises $365 Million to Back Cybersecurity and AI Startups
The Israel-based venture firm now manages close to $2 billion in assets and is betting its newest fund on AI-native companies solving real enterprise security problems.