用少量后门数据验证大模型微调是否真实进行
vTune: Verifiable Fine-Tuning for LLMs Through Backdooring
- 在训练数据中加入少量后门点，通过统计检验验证微调是否真实发生
- 实验显示p值低至10^-40，且不影响下游任务性能
- 适用于开源与闭源模型，对多种攻击有强鲁棒性
随着大语言模型微调的普及，用户往往依赖第三方服务，但缺乏对其微调过程的透明度。例如，服务商可能声称已为每位用户定制微调，实则仅返回原始模型。为此，我们提出vTune，一种通过在训练数据中添加少量后门数据点，实现对微调过程的统计验证方法。该方法可扩展至主流大模型，支持开源与闭源模型。我们在多个模型家族、尺寸及指令微调数据集上测试，发现统计检验的p值约为10^-40，且未影响下游任务表现。进一步评估了多种攻击手段，证明vTune具有强鲁棒性。
原文摘要 · Abstract (English)
As fine-tuning large language models (LLMs) becomes increasingly prevalent, users often rely on third-party services with limited visibility into their fine-tuning processes. This lack of transparency raises the question: how do consumers verify that fine-tuning services are performed correctly? For instance, a service provider could claim to fine-tune a model for each user, yet simply send all users back the same base model. To address this issue, we propose vTune, a simple method that uses a small number of backdoor data points added to the training data to provide a statistical test for verifying that a provider fine-tuned a custom model on a particular user's dataset. Unlike existing works, vTune is able to scale to verification of fine-tuning on state-of-the-art LLMs, and can be used both with open-source and closed-source models. We test our approach across several model families and sizes as well as across multiple instruction-tuning datasets, and find that the statistical test is satisfied with p-values on the order of $\sim 10^{-40}$, with no negative impact on downstream task performance. Further, we explore several attacks that attempt to subvert vTune and demonstrate the method's robustness to these attacks.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。