Hey, welcome to u9up
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.
Deep dives into AI security blind spots — written by people who actually break them.
A deep dive into Model Context Protocol (MCP) — what it is, why it matters, and how to securely build and deploy an MCP server on Google Cloud Run. Presented at GDG Kuala Lumpur Build with AI.
How real attackers approach AI systems. A collaborative deep dive into offensive techniques, exploits, and blind spots that make modern AI applications vulnerable.
As AI agents gain autonomy, so does their attack surface. A breakdown of how agentic systems get exploited and the defence-in-depth strategies to keep them in check.
A threat modelling approach to building safer AI applications, covering prompt injection, backdoor triggers, and Google's Secure AI Framework with Gemini's built-in safeguards.
AI security isn't just about breaking things or defending them — it's both. We research across the full spectrum.
Finding the cracks before the bad actors do. We research attack vectors, test guardrails, and publish what we find so the community can learn.
Building resilience into AI systems. We study detection techniques, guardrail architectures, and monitoring strategies that actually work in production.
Workshops, talks, and the occasional makan session.
Whether you're deep into adversarial ML or just getting curious about AI security — pull up a chair.
