ThreatVectr
Tag

#Black Hat 2026

23 stories taggedBlack Hat 2026 · page 2 of 2.

A split-screen view showing an AI interface window on one side and detailed real-time command logs on the other, with each executed action highlighted and track
AI Security

Airlock Digital Wants to Watch What Your AI Assistant Actually Does, Not Just Whether It's Allowed to Run

A new product layer from Airlock Digital tracks AI agents command by command, in real time, on the devices where they do their work.

3 min read
Black Hat Las Vegas conference floor with vendors presenting security product booths, large display screens showing new tool demonstrations, attendees examining
AI Security

Black Hat 2026: Every Major Security Product Launch You Need to Know

Fifteen vendors dropped new tools at Las Vegas this week. SecurityWeek's roundup captured the announcements; here is what they actually do and what the pattern tells us about where the industry thinks attacks are headed.

4 min read
A cloud architecture diagram with forgotten digital keys scattered throughout the infrastructure, an AI agent waking up and making unexpected requests at odd ho
Identity & Access

The 'Ghost Credentials' Problem: How Forgotten Digital Keys Are Leaving Cloud Systems Wide Open

A sleeping AI agent that woke up and started making requests at odd hours led a security researcher to a sprawling mess of forgotten digital keys, and a free tool to help organisations find them before attackers do.

4 min read
A research lab workspace with multiple monitors displaying abstract neural network visualizations and data flows in real-time, with a researcher's hand pointing
AI Security

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.

4 min read
Illustration: smooth river stones arranged in a row on a wooden surface, each stone casting a soft shadow
Vulnerabilities

The Safety System Keeping 6 GHz Wi-Fi Away From Critical Infrastructure Has Serious Holes

Researchers say the automated gatekeeper that stops modern Wi-Fi from crashing radio towers and public safety networks can be tricked, and some equipment makers are slow to take it seriously.

4 min read
Close-up overhead shot of a plain laptop keyboard in a dimly lit office, the screen glowing pale blue, an inbox interface faintly reflected on the desk surface,
AI Security

ScamBuster Turns Phishing Emails Into Intelligence by Pretending to Be the Victim

A French engineer built an AI system that replies to scam emails, plays along long enough to extract bank details and phone numbers, then hands the data to investigators.

3 min read
Illustration: a modern bank ATM machine
Vulnerabilities

Nine Security Flaws Found in ATM Encryption Software, and Nobody Agrees How Bad It Is

A researcher found serious bugs in software that locks ATM hard drives. The world's biggest ATM maker says they don't matter. The researcher disagrees. The truth is somewhere uncomfortable.

4 min read
Illustration: a boldly patterned geometric hoodie hanging on a plain concrete wall under harsh fluorescent light
AI Security

This Researcher Is Designing Clothes That Break Facial Recognition Software

A security researcher plans to unveil clothing patterns that confuse the AI systems governments use to track people in public, without their knowledge or consent.

4 min read
© 2026 Threat Vectr