1
Defending Against Malicious Finetuning by Scaling Train-time Adversarial Attacks
通过扩大训练时对抗攻击规模，提出防御恶意微调的新范式，为AI模型安全提供可扩展方案。
arXiv:2606.07970v1 Announce Type: new Abstract: Current open-weight large language models (LLMs) are prone to malicious finetuning attacks, which coul…