用零知识证明让模型解释可信，防篡改。
ExpProof : Operationalizing Explanations for Confidential Models with ZKPs
- 用零知识证明技术保障解释过程的可验证性。
- 在神经网络与随机森林上测试了改进后的LIME算法。
- 适合需要可信解释的金融、医疗等高风险场景。
理论上，解释旨在提升对机器学习模型的信任，并常受法规要求。然而，在许多需要解释的场景中，各方利益不一致且存在恶意操纵动机，导致现有解释方法在对抗环境中失效。本文提出通过零知识证明（ZKPs）实现对抗环境下解释的可操作性，探索了适用于ZKP的流行解释算法LIME版本，并在神经网络和随机森林上评估其性能。代码已公开于https://github.com/emlaufer/ExpProof。
原文摘要 · Abstract (English)
In principle, explanations are intended as a way to increase trust in machine learning models and are often obligated by regulations. However, many circumstances where these are demanded are adversarial in nature, meaning the involved parties have misaligned interests and are incentivized to manipulate explanations for their purpose. As a result, explainability methods fail to be operational in such settings despite the demand \cite{bordt2022post}. In this paper, we take a step towards operationalizing explanations in adversarial scenarios with Zero-Knowledge Proofs (ZKPs), a cryptographic primitive. Specifically we explore ZKP-amenable versions of the popular explainability algorithm LIME and evaluate their performance on Neural Networks and Random Forests. Our code is publicly available at https://github.com/emlaufer/ExpProof.
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。