English
Related papers

Related papers: Towards More Robust Interpretation via Local Gradi…

200 papers

The existence of adversarial data examples has drawn significant attention in the deep-learning community; such data are seemingly minimally perturbed relative to the original data, but lead to very different outputs from a deep-learning…

Machine Learning · Computer Science 2019-11-12 Bai Li , Changyou Chen , Wenlin Wang , Lawrence Carin

With the proliferation of Deep Machine Learning into real-life applications, a particular property of this technology has been brought to attention: robustness Neural Networks notoriously present low robustness and can be highly sensitive…

Computation and Language · Computer Science 2022-07-14 Marco Casadio , Ekaterina Komendantskaya , Verena Rieser , Matthew L. Daggitt , Daniel Kienitz , Luca Arnaboldi , Wen Kokke

We study the problem of attributing the prediction of a deep network to its input features, a problem previously studied by several other works. We identify two fundamental axioms---Sensitivity and Implementation Invariance that attribution…

Machine Learning · Computer Science 2017-06-14 Mukund Sundararajan , Ankur Taly , Qiqi Yan

It has been shown that instead of learning actual object features, deep networks tend to exploit non-robust (spurious) discriminative features that are shared between training and test sets. Therefore, while they achieve state of the art…

Machine Learning · Statistics 2019-11-19 Devansh Arpit , Caiming Xiong , Richard Socher

Despite extensive research since the community learned about adversarial examples 10 years ago, we still do not know how to train high-accuracy classifiers that are guaranteed to be robust to small perturbations of their inputs. Previous…

Computer Vision and Pattern Recognition · Computer Science 2025-07-18 Bernd Prach , Christoph H. Lampert

The growing reliance on deep learning models in safety-critical domains such as healthcare and autonomous navigation underscores the need for defenses that are both robust to adversarial perturbations and transparent in their…

Machine Learning · Computer Science 2026-01-06 Longwei Wang , Mohammad Navid Nayyem , Abdullah Al Rakin , KC Santosh , Chaowei Zhang , Yang Zhou

Deep learning interpretation is essential to explain the reasoning behind model predictions. Understanding the robustness of interpretation methods is important especially in sensitive domains such as medical applications since…

Machine Learning · Computer Science 2019-10-21 Alexander Levine , Sahil Singla , Soheil Feizi

While the traditional formulation of machine learning tasks is in terms of performance on average, in practice we are often interested in how well a trained model performs on rare or difficult data points at test time. To achieve more…

Machine Learning · Computer Science 2025-12-29 Matthew J. Holland , Toma Hamada

Deep neural networks are easily fooled by small perturbations known as adversarial attacks. Adversarial Training (AT) is a technique aimed at learning features robust to such attacks and is widely regarded as a very effective defense.…

Machine Learning · Computer Science 2020-09-11 Theodoros Tsiligkaridis , Jay Roberts

Adversarial robustness corresponds to the susceptibility of deep neural networks to imperceptible perturbations made at test time. In the context of image tasks, many algorithms have been proposed to make neural networks robust to…

Computer Vision and Pattern Recognition · Computer Science 2020-12-03 Pranjal Awasthi , George Yu , Chun-Sung Ferng , Andrew Tomkins , Da-Cheng Juan

Deep neural networks are capable of training fast and generalizing well within many domains. Despite their promising performance, deep networks have shown sensitivities to perturbations of their inputs (e.g., adversarial examples) and their…

Machine Learning · Computer Science 2020-07-09 Justin Goodwin , Olivia Brown , Victoria Helus

Gradient-based interpretations often require an anchor point of comparison to avoid saturation in computing feature importance. We show that current baselines defined using static functions--constant mapping, averaging or blurring--inject…

Machine Learning · Computer Science 2025-02-12 Ching Lam Choi , Alexandre Duplessis , Serge Belongie

Neural networks trained on visual data are well-known to be vulnerable to often imperceptible adversarial perturbations. The reasons for this vulnerability are still being debated in the literature. Recently Ilyas et al. (2019) showed that…

Machine Learning · Computer Science 2021-02-11 Jacob M. Springer , Melanie Mitchell , Garrett T. Kenyon

Invariance to nuisance transformations is one of the desirable properties of effective representations. We consider transformations that form a \emph{group} and propose an approach based on kernel methods to derive local group invariant…

Machine Learning · Computer Science 2017-05-25 Anant Raj , Abhishek Kumar , Youssef Mroueh , P. Thomas Fletcher , Bernhard Schölkopf

To explain predictions made by complex machine learning models, many feature attribution methods have been developed that assign importance scores to input features. Some recent work challenges the robustness of these methods by showing…

Machine Learning · Computer Science 2023-11-01 Chris Lin , Ian Covert , Su-In Lee

Gradient-based saliency methods such as Vanilla Gradient (VG) and Integrated Gradients (IG) are widely used to explain image classifiers, yet the resulting maps are often noisy and unstable, limiting their usefulness in high-stakes…

Computer Vision and Pattern Recognition · Computer Science 2026-03-10 Dipkamal Bhusal , Md Tanvirul Alam , Nidhi Rastogi

In deep learning applications, the architectures of deep neural networks are crucial in achieving high accuracy. Many methods have been proposed to search for high-performance neural architectures automatically. However, these searched…

Machine Learning · Computer Science 2020-12-14 Ramtin Hosseini , Xingyi Yang , Pengtao Xie

We demonstrate that the choice of optimizer, neural network architecture, and regularizer significantly affect the adversarial robustness of linear neural networks, providing guarantees without the need for adversarial training. To this…

Machine Learning · Computer Science 2021-06-08 Fartash Faghri , Sven Gowal , Cristina Vasconcelos , David J. Fleet , Fabian Pedregosa , Nicolas Le Roux

Graph Neural Networks (GNNs) have become the standard for graph representation learning but remain vulnerable to structural perturbations. We propose a novel framework that integrates persistent homology features with stability…

Machine Learning · Computer Science 2025-12-17 Jelena Losic

Deep neural networks for medical image classification often fail to generalize consistently in clinical practice due to violations of the i.i.d. assumption and opaque decision-making. This paper examines interpretability in deep neural…

Computer Vision and Pattern Recognition · Computer Science 2025-04-09 Mohammad Hossein Najafi , Mohammad Morsali , Mohammadreza Pashanejad , Saman Soleimani Roudi , Mohammad Norouzi , Saeed Bagheri Shouraki