ExpProof : Operationalizing Explanations for Confidential Models with ZKPs

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.

@article{yadav2025_2502.03773,
  title={ ExpProof : Operationalizing Explanations for Confidential Models with ZKPs },
  author={ Chhavi Yadav and Evan Monroe Laufer and Dan Boneh and Kamalika Chaudhuri },
  journal={arXiv preprint arXiv:2502.03773},
  year={ 2025 }
}