Large language models (LLMs) have shown great potential as general-purpose AI
assistants in various domains. To meet the requirements of different
applications, LLMs are often customized by further fine-tuning. However, the
powerful learning ability of LLMs not only enables them to acquire new tasks
but also makes them susceptible to learning undesired behaviors. For example,
even safety-aligned LLMs can be easily fine-tuned into harmful assistants as
the fine-tuning data often contains implicit or explicit harmful content. Can
we train LLMs on harmful data without learning harmful behaviors? This paper
proposes a controllable training framework that makes harmful behaviors
unlearnable during the fine-tuning process. Specifically, we introduce
``security vectors'', a few new parameters that can be separated from the LLM,
to ensure LLM's responses are consistent with the harmful behavior. Security
vectors are activated during fine-tuning, the consistent behavior makes LLM
believe that such behavior has already been learned, there is no need to
further optimize for harmful data. During inference, we can deactivate security
vectors to restore the LLM's normal behavior. The experimental results show
that the security vectors generated by 100 harmful samples are enough to
prevent LLM from learning 1000 harmful samples, while preserving the ability to
learn other useful information.

通过引入安全向量 `security vectors` 并在微调过程中激活，使得大型语言模型 `LLMs` 产生一致性响应，从而防止其学习有害行为。在推断过程中，我们可以关闭安全向量以恢复正常行为。实验结果表明，使用 100 个有害样本生成的安全向量足以防止 LLM 学习 1000 个有害样本，同时保留学习其他有用信息的能力。