paper-with-me

홈 › Papers

A Game-theoretic Understanding of Repeated Explanations in ML Models

2022-02-05 · Kavita Kumari, Murtuza Jadliwala, Sumit Kumar Jha, Anindya Maiti

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.

📄 PDF Abstract BibTeX arXiv:2202.02659

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

ADESSE: Advice Explanations in Complex Repeated Decision-Making Environments

2024-05-31 · Sören Schleibaum, Lu Feng, Sarit Kraus, Jörg P. Müller

In the evolving landscape of human-centered AI, fostering a synergistic relationship between humans and AI agents in decision-making processes stands as a paramount challenge. This work considers a problem setup where an…

Decision MakingDeep Reinforcement Learning

Towards a Game-theoretic Understanding of Explanation-based Membership Inference Attacks

2024-04-10 · Kavita Kumari, Murtuza Jadliwala, Sumit Kumar Jha, Anindya Maiti

Model explanations improve the transparency of black-box machine learning (ML) models and their decisions; however, they can also be exploited to carry out privacy threats such as membership inference attacks (MIA). Exis…

Evolutionary dynamics of zero-determinant strategies in repeated multiplayer games

2021-09-14 · Fang Chen, Te Wu, Long Wang

Since Press and Dyson's ingenious discovery of ZD (zero-determinant) strategy in the repeated Prisoner's Dilemma game, several studies have confirmed the existence of ZD strategy in repeated multiplayer social dilemmas. …

State-clustering method of payoff computation in repeated multiplayer games

2021-08-24 · Fang Chen, Te Wu, Guocheng Wang, Long Wang

Direct reciprocity is a well-known mechanism that could explain how cooperation emerges and prevails in an evolving population. Numerous prior researches have studied the emergence of cooperation in multiplayer games. Ho…

Clustering

On the Connection between Game-Theoretic Feature Attributions and Counterfactual Explanations

2023-07-13 · Emanuele Albini, Shubham Sharma, Saumitra Mishra, Danial Dervovic 외

Explainable Artificial Intelligence (XAI) has received widespread interest in recent years, and two of the most popular types of explanations are feature attributions, and counterfactual explanations. These classes of ap…

counterfactualCounterfactual ExplanationExplainable artificial intelligenceExplainable Artificial Intelligence (XAI)+1