Deep Ignorance: Filtering Pretraining Data Builds Tamper-Resistant Safeguards into Open-Weight LLMs

Understand

Open-weight AI systems offer unique benefits, including enhanced transparency, open research, and decentralized access.

• However, they are vulnerable to tampering attacks which can efficiently elicit harmful behaviors by modifying weights or activations.
• Currently, there is not yet a robust science of open-weight model risk management.
• Existing safety fine-tuning methods and other post-training techniques have struggled to make LLMs resistant to more than a few dozen steps of adversarial fine-tuning.