提出隐私保护微调新方法，让本地运行的语言模型更安全
DP-Adam-AC: Privacy-preserving Fine-Tuning of Localizable Language Models Using Adam Optimization with Adaptive Clipping
- 用自适应梯度裁剪改进DP-Adam优化器，提升隐私保护能力
- 在两个合成数据集上验证，损失下降明显，微调效果更好
- 适合关注数据隐私的本地化语言模型开发者
大型语言模型（如ChatGPT）已成通用工具。小规模数据微调可高效赋予模型特定任务能力。然而，传统模型受限于硬件要求，难以在消费级设备上本地运行，常需远程连接服务器，易受网络攻击；且敏感任务微调可能泄露训练数据，非私有算法易遭数据复现攻击。本文通过增强差分隐私优化算法，实现本地化语言模型的安全微调。提出自适应梯度裁剪的DP-Adam-AC优化器，并应用于两个可本地运行的模型：Qwen2.5-0.5B与Bitnet-b1.58-2B（1.58 bit量化）。实验使用两个合成数据集，结果显示损失显著降低，微调性能提升明显。
原文摘要 · Abstract (English)
Large language models (LLMs) such as ChatGPT have evolved into powerful and ubiquitous tools. Fine-tuning on small datasets allows LLMs to acquire specialized skills for specific tasks efficiently. Although LLMs provide great utility in both general and task-specific use cases, they are limited by two security-related concerns. First, traditional LLM hardware requirements make them infeasible to run locally on consumer-grade devices. A remote network connection with the LLM provider's server is usually required, making the system vulnerable to network attacks. Second, fine-tuning an LLM for a sensitive task may involve sensitive data. Non-private fine-tuning algorithms produce models vulnerable to training data reproduction attacks. Our work addresses these security concerns by enhancing differentially private optimization algorithms and applying them to fine-tune localizable language models. We introduce adaptable gradient clipping along with other engineering enhancements to the standard DP-Adam optimizer to create DP-Adam-AC. We use our optimizer to fine-tune examples of two localizable LLM designs, small language model (Qwen2.5-0.5B) and 1.58 bit quantization (Bitnet-b1.58-2B). We demonstrate promising improvements in loss through experimentation with two synthetic datasets.
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。