paper-with-me

홈 › Papers

On the interplay of Explainability, Privacy and Predictive Performance with Explanation-assisted Model Extraction

2025-05-13 · Fatima Ezzeddine, Rinad Akel, Ihab Sbeity, Silvia Giordano, Marc Langheinrich, Omran Ayoub

Machine Learning as a Service (MLaaS) has gained important attraction as a means for deploying powerful predictive models, offering ease of use that enables organizations to leverage advanced analytics without substantial investments in specialized infrastructure or expertise. However, MLaaS platforms must be safeguarded against security and privacy attacks, such as model extraction (MEA) attacks. The increasing integration of explainable AI (XAI) within MLaaS has introduced an additional privacy challenge, as attackers can exploit model explanations particularly counterfactual explanations (CFs) to facilitate MEA. In this paper, we investigate the trade offs among model performance, privacy, and explainability when employing Differential Privacy (DP), a promising technique for mitigating CF facilitated MEA. We evaluate two distinct DP strategies: implemented during the classification model training and at the explainer during CF generation.

📄 PDF Abstract BibTeX arXiv:2505.08847

Code (0)

등록된 구현이 없습니다.

Tasks

counterfactualModel extraction

Methods 이 논문이 사용한 방법론

Golden Queue Managers 설명 없음

Similar Papers 제목 키워드 기반

DeepLeak: Privacy Enhancing Hardening of Model Explanations Against Membership Leakage

2026-01-06 · Firas Ben Hmida, Zain Sbeih, Philemon Hailemariam, Birhanu Eshete arxiv

Machine learning (ML) explainability is central to algorithmic transparency in high-stakes settings such as predictive diagnostics and loan approval. However, these same domains require rigorous privacy guaranties, creat…

Explanations Leak: Membership Inference with Differential Privacy and Active Learning Defense

2026-02-03 · Fatima Ezzeddine, Osama Zammar, Silvia Giordano, Omran Ayoub arxiv

Counterfactual explanations (CFs) are increasingly integrated into Machine Learning as a Service (MLaaS) systems to improve transparency; however, ML models deployed via APIs are already vulnerable to privacy attacks suc…

Model extractionActive Learning

Differential Privacy for Anomaly Detection: Analyzing the Trade-off Between Privacy and Explainability

2024-04-09 · Fatima Ezzeddine, Mirna Saad, Omran Ayoub, Davide Andreoletti 외

Anomaly detection (AD), also referred to as outlier detection, is a statistical process aimed at identifying observations within a dataset that significantly deviate from the expected pattern of the majority of the data.…

Anomaly DetectionOutlier Detection

Fixed Point Explainability

2025-05-18 · Emanuele La Malfa, Jon Vadillo, Marco Molinari, Michael Wooldridge

This paper introduces a formal notion of fixed point explanations, inspired by the "why regress" principle, to assess, through recursive applications, the stability of the interplay between a model and its explainer. Fix…

On Explaining Unfairness: An Overview

2024-02-16 · Christos Fragkathoulas, Vasiliki Papanikou, Danae Pla Karidi, Evaggelia Pitoura

Algorithmic fairness and explainability are foundational elements for achieving responsible AI. In this paper, we focus on their interplay, a research area that is recently receiving increasing attention. To this end, we…

Fairness