Defending Against Model Weight Exfiltration Through Inference Verification — LessWrong
Anthropic has adopted upload limits to prevent model weight exfiltration. The idea is simple: model weights are very large, text outputs are small, so if we cap the output bandwidth, we can make model weight transfer take a long time. The problem is that inference servers now generate an enormous amount of tokens (on the order of ~1TB tokens per day), and the output text channel is the one channel you can't easily restrict. Nonetheless, in this work we find that it’s possible to dramatically limit the amount of information an adversary can send using those output tokens. This is because LLM inference is nearly deterministic: if you fix the sampling seed and regenerate an output, over ~98% of tokens match exactly. This means an attacker attempting to send secret information via steganography, the practice of embedding hidden messages inside otherwise normal-looking text, has very little entropy in the user channel to work with. We show that steganographic exfiltration can be limited to