English
Related papers

Related papers: Fool SHAP with Stealthily Biased Sampling

200 papers

Before deploying a black-box model in high-stakes problems, it is important to evaluate the model's performance on sensitive subpopulations. For example, in a recidivism prediction task, we may wish to identify demographic groups for which…

Methodology · Statistics 2023-06-09 John J. Cherian , Emmanuel J. Candès

Training robust deep learning models for down-stream tasks is a critical challenge. Research has shown that down-stream models can be easily fooled with adversarial inputs that look like the training data, but slightly perturbed, in a way…

Machine Learning · Computer Science 2021-01-19 Mahmoud Hossam , Trung Le , He Zhao , Dinh Phung

Explaining the predictions of opaque machine learning algorithms is an important and challenging task, especially as complex models are increasingly used to assist in high-stakes decisions such as those arising in healthcare and finance.…

Machine Learning · Computer Science 2022-06-29 David S. Watson

We evaluate two popular local explainability techniques, LIME and SHAP, on a movie recommendation task. We discover that the two methods behave very differently depending on the sparsity of the data set. LIME does better than SHAP in dense…

Machine Learning · Computer Science 2022-06-13 Claudia V. Roberts , Ehtsham Elahi , Ashok Chandrashekar

As black box explanations are increasingly being employed to establish model credibility in high-stakes settings, it is important to ensure that these explanations are accurate and reliable. However, prior work demonstrates that…

Machine Learning · Computer Science 2021-11-09 Dylan Slack , Sophie Hilgard , Sameer Singh , Himabindu Lakkaraju

Adversarial sample attacks perturb benign inputs to induce DNN misbehaviors. Recent research has demonstrated the widespread presence and the devastating consequences of such attacks. Existing defense techniques either assume prior…

Machine Learning · Computer Science 2018-10-30 Guanhong Tao , Shiqing Ma , Yingqi Liu , Xiangyu Zhang

This paper investigates a unexplored yet impactful vulnerability in AI explainability used in intrusion detection (IDS): multicollinearity-induced instability. Despite extensive reliance on post-hoc explainability tools such as SHAP or…

Machine Learning · Computer Science 2026-05-22 Ioannis J. Vourganas , Anna Lito Michala

Shapley values are widely used to explain black-box models, but they are costly to calculate because they require many model evaluations. We introduce FastSHAP, a method for estimating Shapley values in a single forward pass using a learned…

Machine Learning · Statistics 2022-03-24 Neil Jethani , Mukund Sudarshan , Ian Covert , Su-In Lee , Rajesh Ranganath

Explainable AI (XAI) is an increasingly important area of machine learning research, which aims to make black-box models transparent and interpretable. In this paper, we propose a novel approach to XAI that uses the so-called counterfactual…

Artificial Intelligence · Computer Science 2023-08-02 Bastian Pfeifer , Mateusz Krzyzinski , Hubert Baniecki , Anna Saranti , Andreas Holzinger , Przemyslaw Biecek

Diffusion models have shown their effectiveness in generation tasks by well-approximating the underlying probability distribution. However, diffusion models are known to suffer from an amplified inherent bias from the training data in terms…

Machine Learning · Computer Science 2024-10-04 Yujin Choi , Jinseong Park , Hoki Kim , Jaewook Lee , Saerom Park

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

Clustering algorithms are used in a large number of applications and play an important role in modern machine learning-- yet, adversarial attacks on clustering algorithms seem to be broadly overlooked unlike supervised learning. In this…

Machine Learning · Computer Science 2019-11-19 Anshuman Chhabra , Abhishek Roy , Prasant Mohapatra

We develop a method for generating causal post-hoc explanations of black-box classifiers based on a learned low-dimensional representation of the data. The explanation is causal in the sense that changing learned latent factors produces a…

Machine Learning · Computer Science 2020-10-23 Matthew O'Shaughnessy , Gregory Canal , Marissa Connor , Mark Davenport , Christopher Rozell

Weak supervision enables efficient development of training sets by reducing the need for ground truth labels. However, the techniques that make weak supervision attractive -- such as integrating any source of signal to estimate unknown…

Machine Learning · Computer Science 2023-11-30 Changho Shin , Sonia Cromp , Dyah Adila , Frederic Sala

Deepfake detection models face two critical challenges: generalization to unseen manipulations and demographic fairness among population groups. However, existing approaches often demonstrate that these two objectives are inherently…

Machine Learning · Computer Science 2025-07-04 Harry Cheng , Ming-Hui Liu , Yangyang Guo , Tianyi Wang , Liqiang Nie , Mohan Kankanhalli

Algorithmic fairness has aroused considerable interests in data mining and machine learning communities recently. So far the existing research has been mostly focusing on the development of quantitative metrics to measure algorithm…

Machine Learning · Computer Science 2021-08-12 Weishen Pan , Sen Cui , Jiang Bian , Changshui Zhang , Fei Wang

Black box attacks, where adversaries have limited knowledge of the target model, pose a significant threat to machine learning systems. Adversarial examples generated with a substitute model often suffer from limited transferability to the…

Machine Learning · Computer Science 2024-10-22 Bar Avraham , Yisroel Mirsky

Transferable adversarial attack is always in the spotlight since deep learning models have been demonstrated to be vulnerable to adversarial samples. However, existing physical attack methods do not pay enough attention on transferability…

Computer Vision and Pattern Recognition · Computer Science 2022-05-20 Yu Zhang , Zhiqiang Gong , Yichuang Zhang , YongQian Li , Kangcheng Bin , Jiahao Qi , Wei Xue , Ping Zhong

In this work, we examine Asymmetric Shapley Values (ASV), a variant of the popular SHAP additive local explanation method. ASV proposes a way to improve model explanations incorporating known causal relations between variables, and is also…

Machine Learning · Computer Science 2023-10-17 Domokos M. Kelen , Mihály Petreczky , Péter Kersch , András A. Benczúr

Current AI regulations require discarding sensitive features (e.g., gender, race, religion) in the algorithm's decision-making process to prevent unfair outcomes. However, even without sensitive features in the training set, algorithms can…

Machine Learning · Computer Science 2023-08-29 Giandomenico Cornacchia , Vito Walter Anelli , Fedelucio Narducci , Azzurra Ragone , Eugenio Di Sciascio
‹ Prev 1 8 9 10 Next ›