[Resource Topic] 2023/1859: XorSHAP: Privacy-Preserving Explainable AI for Decision Tree Models

Welcome to the resource topic for 2023/1859

XorSHAP: Privacy-Preserving Explainable AI for Decision Tree Models

Authors: Dimitar Jetchev, Marius Vuille


Explainable AI (XAI) refers to the development of AI systems and machine learning models in a way that humans can understand, interpret and trust the predictions, decisions and outputs of these models. A common approach to explainability is feature importance, that is, determining which input features of the model have the most significant impact on the model prediction. Two major techniques for computing feature importance are LIME (Local Interpretable Model-agnostic Explanations) and SHAP (SHapley Additive exPlanations). While very generic, these methods are computationally expensive even in plaintext. Applying them in the privacy-preserving setting when part or all of the input data is private is therefore a major computational challenge.
In this paper, we present \texttt{XorSHAP} - the first practical privacy-preserving algorithm for computing Shapley values for decision tree ensemble models in the semi-honest Secure Multiparty Computation (SMPC) setting with full threshold. Our algorithm has complexity O(T \widetilde{M} D 2^D), where T is the number of decision trees in the ensemble, D is the depth of the decision trees and \widetilde{M} is the maximum of the number of features M and 2^D (the number of leaf nodes of a tree), and scales to real-world datasets. Our implementation is based on Inpher’s \texttt{Manticore} framework and simultaneously computes (in the SMPC setting) the Shapley values for 100 samples for an ensemble of T = 60 trees of depth D = 4 and M = 100 features in just 7.5 minutes, meaning that the Shapley values for a single prediction are computed in just 4.5 seconds for the same decision tree ensemble model.
Additionally, it is parallelization-friendly, thus, enabling future work on massive hardware acceleration with GPUs.

ePrint: https://eprint.iacr.org/2023/1859

See all topics related to this paper.

Feel free to post resources that are related to this paper below.

Example resources include: implementations, explanation materials, talks, slides, links to previous discussions on other websites.

For more information, see the rules for Resource Topics .