arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2408.03561cs.CRcs.AIcs.LG
收藏

MPC最小化的安全LLM推理

MPC-Minimized Secure LLM Inference

UC Berkeley(加州大学伯克利分校);UC San Diego(加州大学圣迭戈分校)

Deevashwer Rathee, Dacheng Li, Ion Stoica, Hao Zhang, Raluca Popa

AI总结:

Marill框架通过调整LLM微调架构,将昂贵操作移出MPC以最小化安全推理开销,在保持90%以上下游任务性能的同时实现3.6-11.3倍运行时间提升和2.4-6.9倍通信改善。

摘要:

许多基于大型语言模型(LLMs)的推理服务存在隐私问题,要么向服务方泄露用户提示,要么向用户泄露专有权重。安全推理通过安全多方计算(MPC)为这一问题提供了解决方案,但由于MPC带来的巨大开销,它对于现代LLM工作负载仍然不切实际。为了解决这一开销,我们提出了Marill,这是一个通过调整LLM微调来最小化安全推理期间MPC使用的框架。Marill在微调期间引入了高层架构变化,通过移除一些昂贵操作并将另一些操作重新定位到MPC之外而不损害安全性,从而显著减少了推理期间在MPC内部所需的昂贵操作数量。因此,Marill生成的模型在所有安全推理协议上都更加高效,并且我们的方法补充了针对此类操作的MPC友好近似。与标准微调相比,Marill在各种MPC设置下的安全推理中实现了3.6-11.3倍的运行时间提升和2.4-6.9倍的通信改善,同时通常在下游任务上保持超过90%的性能。

英文摘要:

Many inference services based on large language models (LLMs) pose a privacy concern, either revealing user prompts to the service or the proprietary weights to the user. Secure inference offers a solution to this problem through secure multi-party computation (MPC), however, it is still impractical for modern LLM workload due to the large overhead imposed by MPC. To address this overhead, we propose Marill, a framework that adapts LLM fine-tuning to minimize MPC usage during secure inference. Marill introduces high-level architectural changes during fine-tuning that significantly reduce the number of expensive operations needed within MPC during inference, by removing some and relocating others outside MPC without compromising security. As a result, Marill-generated models are more efficient across all secure inference protocols and our approach complements MPC-friendly approximations for such operations. Compared to standard fine-tuning, Marill results in 3.6-11.3x better runtime and 2.4-6.9x better communication during secure inference across various MPC settings, while typically preserving over 90% performance across downstream tasks.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑