Jailbreak to Protect: Buffering and Reinforcing via Temporary Jailbreaking for Safe Fine-Tuning in Large Language Models

ArXi:2605.24550v1 Announce Type: new Fine-tuning-as-a-Service (FaaS) enables personalization of large language models (LLMs), but it can weaken safety-alignment under harmful fine-tuning attacks. Recent work has shown that activating harmful-behavior modules during fine-tuning can prevent models from learning undesired behaviors, but its mechanism remains unclear. In this paper, we revisit temporary jailbreaking as a defense against harmful fine-tuning and provide a gradient-level analysis showing that it saturates safety-degrading gradients while preserving benign task-relevant gradients.