Hey, welcome to u9up

We break it, we fix it, we write about it.

u9up /9up/ verb

An independent AI security community from Malaysia — publishing hands-on research, raising awareness, and sharing what we learn. No gatekeeping, just good research and good vibes.

Breaking AI Agents talk
Breaking AI Agents: A Practical Offensive Security Perspective March 2026
Research

Latest from the lab

Deep dives into AI security blind spots — written by people who actually break them.

Offensive AI

Breaking AI Applications

A Practical Offensive Security Perspective.

What We Do

Two sides of the same coin

AI security isn't just about breaking things or defending them — it's both. We research across the full spectrum.

⚔️

Offensive Security

Finding the cracks before the bad actors do. We research attack vectors, test guardrails, and publish what we find so the community can learn.

Prompt injection Jailbreaks Adversarial ML Model extraction Red teaming Supply chain attacks
🛡️

Defensive Security

Building resilience into AI systems. We study detection techniques, guardrail architectures, and monitoring strategies that actually work in production.

Guardrail design Input validation AI observability Threat detection Model hardening Incident response
Get Involved

Come hang with us.

Whether you're deep into adversarial ML or just getting curious about AI security — pull up a chair.

Research & write-ups
Community discussions
No gatekeeping
Join on LinkedIn