paper-with-me

홈 › Papers

Characterizing the risk of fairwashing

2021-06-14 · NeurIPS 2021 12 · Ulrich Aïvodji, Hiromi Arai, Sébastien Gambs, Satoshi Hara

Fairwashing refers to the risk that an unfair black-box model can be explained by a fairer model through post-hoc explanation manipulation. In this paper, we investigate the capability of fairwashing attacks by analyzing their fidelity-unfairness trade-offs. In particular, we show that fairwashed explanation models can generalize beyond the suing group (i.e., data points that are being explained), meaning that a fairwashed explainer can be used to rationalize subsequent unfair decisions of a black-box model. We also demonstrate that fairwashing attacks can transfer across black-box models, meaning that other black-box models can perform fairwashing without explicitly using their predictions. This generalization and transferability of fairwashing attacks imply that their detection will be difficult in practice. Finally, we propose an approach to quantify the risk of fairwashing, which is based on the computation of the range of the unfairness of high-fidelity explainers.

📄 PDF Abstract BibTeX arXiv:2106.07504

Code (1)

aivodji/characterizing_fairwashing 공식 구현

Tasks

Fairness

Similar Papers 제목 키워드 기반

Mitigating fairwashing using Two-Source Audits

2023-05-23 · Jade Garcia Bourrée, Erwan Le Merrer, Gilles Tredan, Benoît Rottembourg

Recent legislation requires online platforms to provide dedicated APIs to assess the compliance of their decision-making algorithms with the law. Research has nevertheless shown that the auditors of such platforms are pr…

Fairness

Fairwashing: the risk of rationalization

2019-01-28 · Ulrich Aïvodji, Hiromi Arai, Olivier Fortineau, Sébastien Gambs 외

Black-box explanation is the problem of explaining how a machine learning model -- whose internal logic is hidden to the auditor and generally complex -- produces its outcomes. Current approaches for solving this problem…

BIG-bench Machine LearningFairness

What's in a Query: Polarity-Aware Distribution-Based Fair Ranking

2025-02-17 · Aparna Balagopalan, Kai Wang, Olawale Salaudeen, Asia Biega 외

Machine learning-driven rankings, where individuals (or items) are ranked in response to a query, mediate search exposure or attention in a variety of safety-critical settings. Thus, it is important to ensure that such r…

Fairness

Can Explainable AI Explain Unfairness? A Framework for Evaluating Explainable AI

2021-06-14 · Kiana Alikhademi, Brianna Richardson, Emma Drobina, Juan E. Gilbert

Many ML models are opaque to humans, producing decisions too complex for humans to easily understand. In response, explainable artificial intelligence (XAI) tools that analyze the inner workings of a model have been crea…

Explainable artificial intelligenceExplainable Artificial Intelligence (XAI)Fairness

Tag2Risk: Harnessing Social Music Tags for Characterizing Depression Risk

2020-07-26 · Aayush Surana, Yash Goyal, Manish Shrivastava, Suvi Saarikallio 외

Musical preferences have been considered a mirror of the self. In this age of Big Data, online music streaming services allow us to capture ecologically valid music listening behavior and provide a rich source of informa…

valid