English
Related papers

Related papers: Explaining Classifiers using Adversarial Perturbat…

200 papers

In this work, we investigate the phenomenon that robust image classifiers have human-recognizable features -- often referred to as interpretability -- as revealed through the input gradients of their score functions and their subsequent…

Computer Vision and Pattern Recognition · Computer Science 2021-01-14 Jonathan Helland , Nathan VanHoudnos

Adversarial perturbation of images, in which a source image is deliberately modified with the intent of causing a classifier to misclassify the image, provides important insight into the robustness of image classifiers. In this work we…

Computer Vision and Pattern Recognition · Computer Science 2021-03-24 Robert Bassett , Mitchell Graves , Patrick Reilly

Neural networks have demonstrated state-of-the-art performance in various machine learning fields. However, the introduction of malicious perturbations in input data, known as adversarial examples, has been shown to deceive neural network…

Machine Learning · Computer Science 2023-02-06 Dennis Y. Menn , Tzu-hsun Feng , Hung-yi Lee

Adversarial attacks dramatically change the output of an otherwise accurate learning system using a seemingly inconsequential modification to a piece of input data. Paradoxically, empirical evidence indicates that even systems which are…

Machine Learning · Computer Science 2024-09-13 Oliver J. Sutton , Qinghua Zhou , Ivan Y. Tyukin , Alexander N. Gorban , Alexander Bastounis , Desmond J. Higham

Over the past decade, Deep Learning has emerged as a useful and efficient tool to solve a wide variety of complex learning problems ranging from image classification to human pose estimation, which is challenging to solve using statistical…

Computer Vision and Pattern Recognition · Computer Science 2020-05-19 Ashutosh Chaubey , Nikhil Agrawal , Kavya Barnwal , Keerat K. Guliani , Pramod Mehta

It is widely known that convolutional neural networks (CNNs) are vulnerable to adversarial examples: images with imperceptible perturbations crafted to fool classifiers. However, interpretability of these perturbations is less explored in…

Computer Vision and Pattern Recognition · Computer Science 2019-10-02 Kaidi Xu , Sijia Liu , Gaoyuan Zhang , Mengshu Sun , Pu Zhao , Quanfu Fan , Chuang Gan , Xue Lin

In this paper we aim to explore the general robustness of neural network classifiers by utilizing adversarial as well as natural perturbations. Different from previous works which mainly focus on studying the robustness of neural networks…

Computer Vision and Pattern Recognition · Computer Science 2020-10-06 Sadaf Gulshad , Jan Hendrik Metzen , Arnold Smeulders

Adversarial examples raise questions about whether neural network models are sensitive to the same visual features as humans. In this paper, we first detect adversarial examples or otherwise corrupted images based on a class-conditional…

Machine Learning · Computer Science 2020-02-19 Yao Qin , Nicholas Frosst , Sara Sabour , Colin Raffel , Garrison Cottrell , Geoffrey Hinton

Adversarial examples have raised several open questions, such as why they can deceive classifiers and transfer between different models. A prevailing hypothesis to explain these phenomena suggests that adversarial perturbations appear as…

Machine Learning · Computer Science 2025-01-22 Soichiro Kumano , Hiroshi Kera , Toshihiko Yamasaki

We show that adversarial examples, i.e., the visually imperceptible perturbations that result in Convolutional Neural Networks (CNNs) fail, can be alleviated with a mechanism based on foveations---applying the CNN in different image…

Machine Learning · Computer Science 2016-01-20 Yan Luo , Xavier Boix , Gemma Roig , Tomaso Poggio , Qi Zhao

Traditional adversarial attacks typically aim to alter the predicted labels of input images by generating perturbations that are imperceptible to the human eye. However, these approaches often lack explainability. Moreover, most existing…

Computer Vision and Pattern Recognition · Computer Science 2025-04-17 Akram Heidarizadeh , Connor Hatfield , Lorenzo Lazzarotto , HanQin Cai , George Atia

The literature on adversarial attacks in computer vision typically focuses on pixel-level perturbations. These tend to be very difficult to interpret. Recent work that manipulates the latent representations of image generators to create…

Machine Learning · Computer Science 2023-09-12 Stephen Casper , Max Nadeau , Dylan Hadfield-Menell , Gabriel Kreiman

One well motivated explanation method for classifiers leverages counterfactuals which are hypothetical events identical to real observations in all aspects except for one feature. Constructing such counterfactual poses specific challenges…

Machine Learning · Computer Science 2024-09-12 Pirmin Lemberger , Antoine Saillenfest

Machine learning methods in general and Deep Neural Networks in particular have shown to be vulnerable to adversarial perturbations. So far this phenomenon has mainly been studied in the context of whole-image classification. In this…

Machine Learning · Statistics 2017-03-06 Volker Fischer , Mummadi Chaithanya Kumar , Jan Hendrik Metzen , Thomas Brox

We introduce a method for learning adversarial perturbations targeted to individual images or videos. The learned perturbations are found to be sparse while at the same time containing a high level of feature detail. Thus, the extracted…

Computer Vision and Pattern Recognition · Computer Science 2018-09-05 Roberto Rey-de-Castro , Herschel Rabitz

It has been shown that most machine learning algorithms are susceptible to adversarial perturbations. Slightly perturbing an image in a carefully chosen direction in the image space may cause a trained neural network model to misclassify…

Computer Vision and Pattern Recognition · Computer Science 2017-07-13 Jiajun Lu , Hussein Sibai , Evan Fabry , David Forsyth

We study the robustness of machine learning approaches to adversarial perturbations, with a focus on supervised learning scenarios. We find that typical phase classifiers based on deep neural networks are extremely vulnerable to adversarial…

Disordered Systems and Neural Networks · Physics 2024-01-26 Si Jiang , Sirui Lu , Dong-Ling Deng

While adversarial perturbation of images to attack deep image classification models pose serious security concerns in practice, this paper suggests a novel paradigm where the concept of image perturbation can benefit classification…

Computer Vision and Pattern Recognition · Computer Science 2023-12-15 Juyeop Kim , Jun-Ho Choi , Soobeom Jang , Jong-Seok Lee

In this paper we propose a novel method for detecting adversarial examples by training a binary classifier with both origin data and saliency data. In the case of image classification model, saliency simply explain how the model make…

Machine Learning · Computer Science 2018-03-26 Chiliang Zhang , Zhimou Yang , Zuochang Ye

Counterfactuals are a popular framework for interpreting machine learning predictions. These what if explanations are notoriously challenging to create for computer vision models: standard gradient-based methods are prone to produce…

Machine Learning · Computer Science 2025-04-23 Jeremy Goldwasser , Giles Hooker