English
Related papers

Related papers: Robust Counterfactual Explanations for Neural Netw…

200 papers

High sensitivity of neural networks against malicious perturbations on inputs causes security concerns. To take a steady step towards robust classifiers, we aim to create neural network models provably defended from perturbations. Prior…

Computer Vision and Pattern Recognition · Computer Science 2018-11-02 Yusuke Tsuzuku , Issei Sato , Masashi Sugiyama

We tackle the problem of computing counterfactual explanations -- minimal changes to the features that flip an undesirable model prediction. We propose a solution to this question for linear Support Vector Machine (SVMs) models. Moreover,…

Machine Learning · Computer Science 2022-12-16 Sebastian Salazar , Samuel Denton , Ansaf Salleb-Aouissi

In this study, we explore the inherent trade-off between accuracy and robustness in neural networks, drawing an analogy to the uncertainty principle in quantum mechanics. We propose that neural networks are subject to an uncertainty…

Machine Learning · Computer Science 2025-01-17 Jun-Jie Zhang , Dong-Xiao Zhang , Jian-Nan Chen , Long-Gang Pang , Deyu Meng

There exist several methods that aim to address the crucial task of understanding the behaviour of AI/ML models. Arguably, the most popular among them are local explanations that focus on investigating model behaviour for individual…

Machine Learning · Computer Science 2023-01-04 Saumitra Mishra , Sanghamitra Dutta , Jason Long , Daniele Magazzeni

Machine learning models now influence decisions that directly affect people's lives, making it important to understand not only their predictions, but also how individuals could act to obtain better results. Algorithmic recourse provides…

Machine Learning · Computer Science 2026-02-10 Bohdan Turbal , Iryna Voitsitska , Lesia Semenova

Predictive models can fail to generalize from training to deployment environments because of dataset shift, posing a threat to model reliability and the safety of downstream decisions made in practice. Instead of using samples from the…

Machine Learning · Statistics 2018-08-10 Adarsh Subbaswamy , Suchi Saria

Stability of recurrent models is closely linked with trainability, generalizability and in some applications, safety. Methods that train stable recurrent neural networks, however, do so at a significant cost to expressibility. We propose an…

Machine Learning · Computer Science 2019-12-24 Max Revay , Ian R. Manchester

The adoption of increasingly complex deep models has fueled an urgent need for insight into how these models make predictions. Counterfactual explanations form a powerful tool for providing actionable explanations to practitioners.…

Machine Learning · Computer Science 2024-11-05 Paraskevas Pegios , Aasa Feragen , Andreas Abildtrup Hansen , Georgios Arvanitidis

Spurious correlations threaten the validity of statistical classifiers. While model accuracy may appear high when the test data is from the same distribution as the training data, it can quickly degrade when the test distribution changes.…

Machine Learning · Computer Science 2020-12-21 Zhao Wang , Aron Culotta

This paper proposes a class of well-conditioned neural networks in which a unit amount of change in the inputs causes at most a unit amount of change in the outputs or any of the internal layers. We develop the known methodology of…

Artificial Intelligence · Computer Science 2019-02-07 Haifeng Qian , Mark N. Wegman

Models are often given in terms of differential equations to represent physical systems. In the presence of uncertainty, accurate prediction of the behavior of these systems using the models requires understanding the effect of uncertainty…

Computational Physics · Physics 2020-08-12 Subhayan De

We investigate robustness of deep feed-forward neural networks when input data are subject to random uncertainties. More specifically, we consider regularization of the network by its Lipschitz constant and emphasize its role. We highlight…

Machine Learning · Computer Science 2019-04-15 Nicolas Couellan

We have recently witnessed a number of impressive results on hard mathematical reasoning problems with language models. At the same time, the robustness of these models has also been called into question; recent works have shown that models…

Computation and Language · Computer Science 2023-06-09 Alessandro Stolfo , Zhijing Jin , Kumar Shridhar , Bernhard Schölkopf , Mrinmaya Sachan

Survivor bias in observational data leads the optimization of recommender systems towards local optima. Currently most solutions re-mines existing human-system collaboration patterns to maximize longer-term satisfaction by reinforcement…

Machine Learning · Computer Science 2023-10-31 Jialin Liu , Xinyan Su , Peng Zhou , Xiangyu Zhao , Jun Li

Recent advancements in machine learning have emphasized the need for transparency in model predictions, particularly as interpretability diminishes when using increasingly complex architectures. In this paper, we propose leveraging…

Machine Learning · Computer Science 2025-07-18 Chenrui Zhu , Louenas Bounia , Vu Linh Nguyen , Sébastien Destercke , Arthur Hoarau

This paper introduces a new class of explanation structures, called robust counterfactual witnesses (RCWs), to provide robust, both counterfactual and factual explanations for graph neural networks. Given a graph neural network M, a robust…

Machine Learning · Computer Science 2024-05-01 Dazhuo Qiu , Mengying Wang , Arijit Khan , Yinghui Wu

We introduce a criterion, resilience, which allows properties of a dataset (such as its mean or best low rank approximation) to be robustly computed, even in the presence of a large fraction of arbitrary additional data. Resilience is a…

Machine Learning · Computer Science 2017-11-28 Jacob Steinhardt , Moses Charikar , Gregory Valiant

The threat of adversarial examples has motivated work on training certifiably robust neural networks to facilitate efficient verification of local robustness at inference time. We formalize a notion of global robustness, which captures the…

Machine Learning · Computer Science 2021-06-15 Klas Leino , Zifan Wang , Matt Fredrikson

Counterexample-guided repair aims at creating neural networks with mathematical safety guarantees, facilitating the application of neural networks in safety-critical domains. However, whether counterexample-guided repair is guaranteed to…

Machine Learning · Computer Science 2023-06-06 David Boetius , Stefan Leue , Tobias Sutter

We introduce Harmonic Robustness, a powerful and intuitive method to test the robustness of any machine-learning model either during training or in black-box real-time inference monitoring without ground-truth labels. It is based on…

Machine Learning · Computer Science 2024-04-30 Nicholas S. Kersting , Yi Li , Aman Mohanty , Oyindamola Obisesan , Raphael Okochu