DETER: Suppression During Pretraining for Tamper Resistance
Maria Ios Glarou, Martin Jaggi
原文摘要
Open-weight language models can acquire knowledge that could enable biological, chemical, or cyber misuse. Any attempt to limit such knowledge must remain effective after the model weights are released and can be fine-tuned. Unlearning applied after pretraining can be rapidly undone, whereas filtering the pretraining corpus offers greater resistance. We ask whether actively suppressing knowledge during pretraining can further increase the fine-tuning required to acquire it. Even simple gradient ascent interleaved with standard pretraining on the filtered corpus makes medical knowledge harder to acquire through adversarial fine-tuning than filtering alone or post-hoc unlearning. At 1B parameters, reaching the held-out PubMed loss of an unfiltered model requires over 20$\times$ as many PubMed fine-tuning tokens as after filtering alone. Retained knowledge is evaluated using both held-out data and downstream tasks. Across model sizes, varying suppression strength reveals an increasingly favorable trade-off between fine-tuning difficulty and held-out loss on retained pretraining data. These results point to pretraining as an effective stage for making unwanted capabilities harder to acquire through subsequent fine-tuning. Code is available at \href{https://github.com/MEGlr/DETER}{\texttt{github.com/MEGlr/DETER}}.
cs.LG