Hands Off: Detecting Model Weight Tampering
- 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.
- Models can be corrupted about a specific topic without a single byte on disk
Unverified
- 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.
- Models can be corrupted about a specific topic without a single byte on disk
Sources: Stealthium