English
Related papers

Related papers: Fooling SHAP with Output Shuffling Attacks

200 papers

As machine learning algorithms are deployed ubiquitously to a variety of domains, it is imperative to make these often black-box models transparent. Several recent works explain black-box models by capturing the most influential features…

Explainable Artificial Intelligence (XAI) is a crucial pathway in mitigating the risk of non-transparency in the decision-making process of black-box Artificial Intelligence (AI) systems. However, despite the benefits, XAI methods are found…

Artificial Intelligence · Computer Science 2025-12-30 Sonal Allana , Rozita Dara , Xiaodong Lin , Pulei Xiong

Counterfactual explanations have emerged as a prominent method in Explainable Artificial Intelligence (XAI), providing intuitive and actionable insights into Machine Learning model decisions. In contrast to other traditional feature…

SHAP (SHapley Additive exPlanations) has become a popular method to attribute the prediction of a machine learning model on an input to its features. One main challenge of SHAP is the computation time. An exact computation of Shapley values…

Machine Learning · Statistics 2023-09-06 Linwei Hu , Ke Wang

Emerging vulnerabilities in machine learning (ML) models due to adversarial attacks raise concerns about their reliability. Specifically, evasion attacks manipulate models by introducing precise perturbations to input data, causing…

Machine Learning · Computer Science 2024-05-03 Vidit Khazanchi , Pavan Kulkarni , Yuvaraj Govindarajulu , Manojkumar Parmar

The trustworthiness of Machine Learning (ML) models can be difficult to assess, but is critical in high-risk or ethically sensitive applications. Many models are treated as a `black-box' where the reasoning or criteria for a final decision…

Machine Learning · Computer Science 2024-07-11 Saif Anwar , Nathan Griffiths , Abhir Bhalerao , Thomas Popham

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 created. Despite these…

Computers and Society · Computer Science 2021-06-17 Kiana Alikhademi , Brianna Richardson , Emma Drobina , Juan E. Gilbert

Explainable Artificial Intelligence (XAI) techniques, such as SHapley Additive exPlanations (SHAP), have become essential tools for interpreting complex ensemble tree-based models, especially in high-stakes domains such as healthcare…

Artificial Intelligence · Computer Science 2026-02-25 Akshat Dubey , Aleksandar Anžel , Bahar İlgen , Georges Hattab

Model explanations provide transparency into a trained machine learning model's blackbox behavior to a model builder. They indicate the influence of different input attributes to its corresponding model prediction. The dependency of…

Cryptography and Security · Computer Science 2022-09-09 Vasisht Duddu , Antoine Boutet

Local feature attribution methods are increasingly used to explain complex machine learning models. However, current methods are limited because they are extremely expensive to compute or are not capable of explaining a distributed series…

Machine Learning · Computer Science 2022-10-12 Hugh Chen , Scott M. Lundberg , Su-In Lee

Feature selection is a classical problem in statistics and machine learning, and it continues to remain an extremely challenging problem especially in the context of unknown non-linear relationships with dependent features. On the other…

Machine Learning · Statistics 2026-04-17 Chenghui Zheng , Garvesh Raskutti

Explainable Artificial Intelligence (XAI) is increasingly required in computational economics, where machine-learning forecasters can outperform classical econometric models but remain difficult to audit and use for policy. This survey…

General Economics · Economics 2025-12-16 Agustín García-García , Pablo Hidalgo , Julio E. Sandubete

An important technique to explore a black-box machine learning (ML) model is called SHAP (SHapley Additive exPlanation). SHAP values decompose predictions into contributions of the features in a fair way. We will show that for a boosted…

Machine Learning · Statistics 2022-08-01 Michael Mayer

We propose a new adversarial attack to Deep Neural Networks for image classification. Different from most existing attacks that directly perturb input pixels, our attack focuses on perturbing abstract features, more specifically, features…

Machine Learning · Computer Science 2020-12-17 Qiuling Xu , Guanhong Tao , Siyuan Cheng , Xiangyu Zhang

The monitoring of rotating machinery is an essential task in today's production processes. Currently, several machine learning and deep learning-based modules have achieved excellent results in fault detection and diagnosis. Nevertheless,…

Artificial Intelligence · Computer Science 2021-02-24 Lucas Costa Brito , Gian Antonio Susto , Jorge Nei Brito , Marcus Antonio Viana Duarte

Deep neural networks obtain state-of-the-art performance on a series of tasks. However, they are easily fooled by adding a small adversarial perturbation to input. The perturbation is often human imperceptible on image data. We observe a…

Machine Learning · Computer Science 2019-06-11 Puyudi Yang , Jianbo Chen , Cho-Jui Hsieh , Jane-Ling Wang , Michael I. Jordan

Explaining complex or seemingly simple machine learning models is an important practical problem. We want to explain individual predictions from a complex machine learning model by learning simple, interpretable explanations. Shapley values…

Machine Learning · Statistics 2020-02-07 Kjersti Aas , Martin Jullum , Anders Løland

Objective: Shapley additive explanations (SHAP) is a popular post-hoc technique for explaining black box models. While the impact of data imbalance on predictive models has been extensively studied, it remains largely unknown with respect…

Machine Learning · Computer Science 2022-06-10 Mingxuan Liu , Yilin Ning , Han Yuan , Marcus Eng Hock Ong , Nan Liu

We propose probabilistic Shapley inference (PSI), a novel probabilistic framework to model and infer sufficient statistics of feature attributions in flexible predictive models, via latent random variables whose mean recovers Shapley…

Machine Learning · Computer Science 2025-09-09 Mert Ketenci , Iñigo Urteaga , Victor Alfonso Rodriguez , Noémie Elhadad , Adler Perotte

A main drawback of eXplainable Artificial Intelligence (XAI) approaches is the feature independence assumption, hindering the study of potential variable dependencies. This leads to approximating black box behaviors by analyzing the effects…

Artificial Intelligence · Computer Science 2024-10-16 Martina Cinquini , Riccardo Guidotti