ThreatVectr
Tag

#ai-security

372 stories taggedai-security · page 8 of 25.

A whiteboard or digital canvas displaying the PHANTOM-B framework with interconnected boxes showing different categories of AI system risks, with a security exp
AI Security

A 15-Minute Framework for Spotting What AI Systems Can Do Wrong

Security expert Adam Shostack built PHANTOM-B to help organisations find the risks hiding inside AI-powered software before those risks find them.

4 min read
A researcher's computer showing a chat interface with an AI assistant, with internal system information and security weaknesses being revealed in the conversati
AI Security

Researchers Tricked Microsoft Copilot Into Revealing Its Own Weaknesses, Then Used That Knowledge to Steal Data

A research team at Varonis discovered that simply chatting with Microsoft's AI assistant could expose enough internal detail to build a working attack. Microsoft has patched the flaws, but the technique raises questions that go well beyond one product.

4 min read
A Copilot AI assistant interface on screen showing connected applications like Gmail and calendar services, with warning indicators highlighting data leakage vu
AI Security

One Click on Copilot Could Have Leaked Your Connected Apps, Researchers Say

Three flaws in Microsoft Copilot Personal, nicknamed CoSnitch, let a booby-trapped link quietly pull data from Gmail, calendars and other services the assistant was connected to.

4 min read
A computer screen displaying code and error messages in red, with overlaid visualization of data packets being intercepted and diverted, representing active exp
Cloud Security

Hackers Are Actively Attacking MLflow and FUXA to Steal Cloud Secrets

Two open-source tools used by AI teams and factory operators are being scanned and broken into in the wild, with attackers using one flaw to grab cloud login keys.

4 min read
A split-screen showing a human security team at workstations on one side and rapidly accelerating attack indicators on the other, with timestamps compressing an
AI Security

Can Defenders Keep Up When AI Speeds Up Every Attack?

A new webinar asks whether 'detect it after it happens' is still a workable security strategy when attackers can move faster than any human team can react.

3 min read
A desk scattered with computer hardware and technical manuals, with lines of code and AI models displayed on multiple monitors, suggesting self-taught expertise
AI Security

From Argentina's Early Hacking Scene to AI-Powered Offensive Security: The Nico Waisman Story

How a self-taught hacker with no formal training built his way to leading security at XBOW, a firm that uses artificial intelligence to find weaknesses before attackers do.

3 min read
A network diagram showing AI coding agents connected by files and prompts, with malicious instructions spreading like contagion through the shared connections,
AI Security

AI Agents Can Infect Each Other Through Shared Prompt Files, Researchers Show

A preprint from Anthropic and EPFL demonstrates self-spreading instructions jumping between coding agents in a lab setup.

3 min read
A corporate acquisition scene with security product icons and AI model testing workflows merging into a single unified platform interface, representing consolid
AI Security

Fortinet Buys AI Security Startup Virtue AI

The cybersecurity giant adds a specialist platform for testing and protecting AI models, chatbots, and autonomous software agents, as the market for AI security tools heats up fast.

4 min read
A split code editor showing vulnerable code written by an AI tool on one side and the same vulnerability being exploited by another AI tool on the other, repres
AI Security

AI is getting better at breaking software than fixing it

Multiple studies show AI tools write insecure code nearly as often as they did a year ago, even as those same tools grow sharper at finding and exploiting the very flaws they leave behind.

5 min read
A server room filled with blinking network equipment and cooling systems, with red warning lights illuminating the hardware, suggesting active threat detection
Vulnerabilities

CISA Adds Actively Exploited Ray AI Framework Flaw to Must-Patch List

The bug in Ray, a popular open-source tool for running AI workloads, is being abused in the wild. CISA gave federal agencies a deadline to fix it.

3 min read
A security conference presentation stage with a speaker addressing an audience of cybersecurity professionals, with AI model architecture diagrams projected beh
AI Security

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.

4 min read
A cybersecurity analyst reviewing multiple data sources on large monitors—network logs, firewall records, DNS queries—while AI analysis tools display insights o
AI Security

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.

4 min read
A desk with multiple monitors showing network diagrams and IP addresses, with one screen displaying an alert notification while files transfer across the networ
AI Security

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.

4 min read
A busy security operations center wall displaying multiple stacked windows and alerts from different security tools, creating a complex layered visual of interc
Threat Intelligence

This Week's Security Grab Bag: AI Hijacks, Fake Fixes, and a Cursor Bug

A roundup week: nothing catastrophic on its own, but the patterns are the story.

4 min read
An autonomous robotic arm in a warehouse setting that has accidentally toppled a stack of packages, with security camera footage timestamp visible in the corner
AI Security

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.

3 min read
© 2026 Threat Vectr