A Game-theoretic Understanding of Repeated Explanations in ML Models
Not on the map. Why?
Abstract (arXiv)
This paper formally models the strategic repeated interactions between a system, comprising of a machine learning (ML) model and associated explanation method, and an end-user who is seeking a prediction/label and its explanation for a query/input, by means of game theory. In this game, a malicious end-user must strategically decide when to stop querying and attempt to compromise the system, while the system must strategically decide how much information (in the form of noisy explanations) it should share with the end-user and when to stop sharing, all without knowing the type (honest/malicious) of the end-user. This paper formally models this trade-off using a continuous-time stochastic Signaling game framework and characterizes the Markov perfect equilibrium state within such a framework.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 9 of its 27 references that are in the map. First posted on arXiv 5 Feb 2022.
Builds on
9 of 27 references.
References · 9
- 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
- 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
- 2017Axiomatic Attribution for Deep Networkscited by 3,350
- 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,348
- 2017Learning Important Features Through Propagating Activation Differencescited by 1,454
- 2019Fooling LIME and SHAP: Adversarial Attacks on Post hoc Explanation Methodscited by 440
- 2016Not Just a Black Box: Learning Important Features Through Propagating Activation Differencescited by 295
- 2016"What is Relevant in a Text Document?": An Interpretable Machine Learning Approachcited by 53
- 2018Understanding Convolutional Neural Networks for Text Classificationcited by 36
Built on by
Not cited yet.