English
Related papers

Related papers: Deep neural network loses attention to adversarial…

200 papers

Adversarial training and adversarial purification are two widely used defense strategies for enhancing model robustness against adversarial attacks. However, adversarial training requires costly retraining, while adversarial purification…

Computer Vision and Pattern Recognition · Computer Science 2025-09-17 Xuelong Dai , Dong Wang , Xiuzhen Cheng , Bin Xiao

Machine learning models, especially deep neural networks (DNNs), have been shown to be vulnerable against adversarial examples which are carefully crafted samples with a small magnitude of the perturbation. Such adversarial perturbations…

Computer Vision and Pattern Recognition · Computer Science 2020-03-23 Anand Bhattad , Min Jin Chong , Kaizhao Liang , Bo Li , D. A. Forsyth

Deep Neural Networks are built to generalize outside of training set in mind by using techniques such as regularization, early stopping and dropout. But considerations to make them more resilient to adversarial examples are rarely taken. As…

Machine Learning · Computer Science 2017-12-27 Arkar Min Aung , Yousef Fadila , Radian Gondokaryono , Luis Gonzalez

Despite a great deal of research, it is still not well-understood why trained neural networks are highly vulnerable to adversarial examples. In this work we focus on two-layer neural networks trained using data which lie on a low…

Machine Learning · Computer Science 2023-11-17 Odelia Melamed , Gilad Yehudai , Gal Vardi

Deep neural networks (DNN) have achieved unprecedented success in numerous machine learning tasks in various domains. However, the existence of adversarial examples has raised concerns about applying deep learning to safety-critical…

Machine Learning · Computer Science 2019-10-10 Han Xu , Yao Ma , Haochen Liu , Debayan Deb , Hui Liu , Jiliang Tang , Anil K. Jain

We investigate the problem of identifying adversarial attacks on image-based neural networks. We present intriguing experimental results showing significant discrepancies between the explanations generated for the predictions of a model on…

Machine Learning · Computer Science 2020-03-13 Sean Saito , Jin Wang

Deep neural networks (DNNs) are threatened by adversarial examples. Adversarial detection, which distinguishes adversarial images from benign images, is fundamental for robust DNN-based services. Image transformation is one of the most…

Computer Vision and Pattern Recognition · Computer Science 2022-05-27 Hui Liu , Bo Zhao , Yuefeng Peng , Weidong Li , Peng Liu

Deep neural networks are vulnerable to adversarial examples, even in the black-box setting where the attacker is only accessible to the model output. Recent studies have devised effective black-box attacks with high query efficiency.…

Machine Learning · Computer Science 2022-06-07 Zeyu Dai , Shengcai Liu , Ke Tang , Qing Li

Deep neural networks (DNNs) have achieved excellent performance on several tasks and have been widely applied in both academia and industry. However, DNNs are vulnerable to adversarial machine learning attacks, in which noise is added to…

Machine Learning · Computer Science 2020-01-01 Huy H. Nguyen , Minoru Kuribayashi , Junichi Yamagishi , Isao Echizen

We propose gradient adversarial training, an auxiliary deep learning framework applicable to different machine learning problems. In gradient adversarial training, we leverage a prior belief that in many contexts, simultaneous gradient…

Machine Learning · Computer Science 2018-06-22 Ayan Sinha , Zhao Chen , Vijay Badrinarayanan , Andrew Rabinovich

Deep Learning models are vulnerable to adversarial examples, i.e.\ images obtained via deliberate imperceptible perturbations, such that the model misclassifies them with high confidence. However, class confidence by itself is an incomplete…

Machine Learning · Statistics 2017-11-23 Ambrish Rawat , Martin Wistuba , Maria-Irina Nicolae

Many machine learning classifiers are vulnerable to adversarial perturbations. An adversarial perturbation modifies an input to change a classifier's prediction without causing the input to seem substantially different to human perception.…

Machine Learning · Computer Science 2017-03-27 Dan Hendrycks , Kevin Gimpel

State-of-the-art convolutional neural network models for object detection and image classification are vulnerable to physically realizable adversarial perturbations, such as patch attacks. Existing defenses have focused, implicitly or…

Computer Vision and Pattern Recognition · Computer Science 2025-06-25 Mauricio Byrd Victorica , György Dán , Henrik Sandberg

The increasing use of deep neural networks (DNNs) has motivated a parallel endeavor: the design of adversaries that profit from successful misclassifications. However, not all adversarial examples are crafted for malicious purposes. For…

Computer Vision and Pattern Recognition · Computer Science 2024-09-18 Pk Douglas , Farzad Vasheghani Farahani

Deep Neural Networks have been shown to be vulnerable to adversarial images. Conventional attacks strive for indistinguishable adversarial images with strictly restricted perturbations. Recently, researchers have moved to explore…

Computer Vision and Pattern Recognition · Computer Science 2023-06-19 Zhengyu Zhao , Zhuoran Liu , Martha Larson

In this paper, we aim to understand and explain the decisions of deep neural networks by studying the behavior of predicted attributes when adversarial examples are introduced. We study the changes in attributes for clean as well as…

Computer Vision and Pattern Recognition · Computer Science 2019-10-17 Sadaf Gulshad , Zeynep Akata , Jan Hendrik Metzen , Arnold Smeulders

Deep learning has become an integral part of various computer vision systems in recent years due to its outstanding achievements for object recognition, facial recognition, and scene understanding. However, deep neural networks (DNNs) are…

Computer Vision and Pattern Recognition · Computer Science 2021-08-24 Nima Mirnateghi , Syed Afaq Ali Shah , Mohammed Bennamoun

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

We introduce a saliency-based distortion layer for convolutional neural networks that helps to improve the spatial sampling of input data for a given task. Our differentiable layer can be added as a preprocessing block to existing task…

Computer Vision and Pattern Recognition · Computer Science 2018-09-11 Adrià Recasens , Petr Kellnhofer , Simon Stent , Wojciech Matusik , Antonio Torralba

Saliency maps are widely used in the computer vision community for interpreting neural network classifiers. However, due to the randomness of training samples and optimization algorithms, the resulting saliency maps suffer from a…

Computer Vision and Pattern Recognition · Computer Science 2024-12-20 Shizhan Gong , Jingwei Zhang , Qi Dou , Farzan Farnia