Detecting model weight tampering in GPU memory (Rome attacks)
- GPU: 37 events in the last 90 days
- Previous: 4 days earlier · Supermicro wants AI factories judged by how fast they go live, not by GPU count
What happened
This article introduces Rank-One Model Editing (ROME) attacks, where a malicious Python module rewrites a model's weights in GPU memory to corrupt its answers, and explains why CPU-focused security tooling misses this class of attack. We then run a ROME attack in our lab and show how Stealthium detects model tampering via our runtime sensor, which ties every CUDA kernel launch back to the Python code that issued it,…
Summary assembled by rule from the sources below