paper-with-me

홈 › Papers

Why You Should Not Trust Interpretations in Machine Learning: Adversarial Attacks on Partial Dependence Plots

2024-04-29 · Xi Xin, Giles Hooker, Fei Huang

The adoption of artificial intelligence (AI) across industries has led to the widespread use of complex black-box models and interpretation tools for decision making. This paper proposes an adversarial framework to uncover the vulnerability of permutation-based interpretation methods for machine learning tasks, with a particular focus on partial dependence (PD) plots. This adversarial framework modifies the original black box model to manipulate its predictions for instances in the extrapolation domain. As a result, it produces deceptive PD plots that can conceal discriminatory behaviors while preserving most of the original model's predictions. This framework can produce multiple fooled PD plots via a single model. By using real-world datasets including an auto insurance claims dataset and COMPAS (Correctional Offender Management Profiling for Alternative Sanctions) dataset, our results show that it is possible to intentionally hide the discriminatory behavior of a predictor and make the black-box model appear neutral through interpretation tools like PD plots while retaining almost all the predictions of the original black-box model. Managerial insights for regulators and practitioners are provided based on the findings.

📄 PDF Abstract BibTeX arXiv:2404.18702

Code (0)

등록된 구현이 없습니다.

Tasks

Decision MakingManagement

Methods 이 논문이 사용한 방법론

Focus 설명 없음

Similar Papers 제목 키워드 기반

Adversarial attacks and defenses in explainable artificial intelligence: A survey

2023-06-06 · Hubert Baniecki, Przemyslaw Biecek

Explainable artificial intelligence (XAI) methods are portrayed as a remedy for debugging and trusting statistical and deep learning models, as well as interpreting their predictions. However, recent advances in adversar…

Decision MakingExplainable artificial intelligenceExplainable Artificial Intelligence (XAI)Fairness+1

Resilience of Bayesian Layer-Wise Explanations under Adversarial Attacks

2021-02-22 · Ginevra Carbone, Guido Sanguinetti, Luca Bortolussi

We consider the problem of the stability of saliency-based explanations of Neural Network predictions under adversarial attacks in a classification task. Saliency interpretations of deterministic Neural Networks are rema…

General Classification

Adversarial Training for Improving Model Robustness? Look at Both Prediction and Interpretation

2022-03-23 · Hanjie Chen, Yangfeng Ji

Neural language models show vulnerability to adversarial examples which are semantically similar to their original counterparts with a few words replaced by their synonyms. A common way to improve model robustness is adv…

text-classificationText Classification

Attacking interpretable NLP systems

2025-07-22 · Eldor Abdukhamidov, Tamer Abuhmed, Joanna C. S. Santos, Mohammed Abuhamad arxiv

Studies have shown that machine learning systems are vulnerable to adversarial examples in theory and practice. Where previous attacks have focused mainly on visual models that exploit the difference between human and ma…

Recent improvements of ASR models in the face of adversarial attacks

2022-03-29 · Raphael Olivier, Bhiksha Raj

Like many other tasks involving neural networks, Speech Recognition models are vulnerable to adversarial attacks. However recent research has pointed out differences between attacks and defenses on ASR models compared to…

speech-recognitionSpeech Recognition