English
Related papers

Related papers: On Saliency Maps and Adversarial Robustness

200 papers

Adversarial training is a training scheme designed to counter adversarial attacks by augmenting the training dataset with adversarial examples. Surprisingly, several studies have observed that loss gradients from adversarially trained DNNs…

Machine Learning · Computer Science 2019-04-22 Beomsu Kim , Junghoon Seo , Taegyun Jeon

Machine learning models are vulnerable to tiny adversarial input perturbations optimized to cause a very large output error. To measure this vulnerability, we need reliable methods that can find such adversarial perturbations. For image…

Computer Vision and Pattern Recognition · Computer Science 2024-07-15 Levente Halmosi , Bálint Mohos , Márk Jelasity

Saliency maps are frequently used to support explanations of the behavior of deep reinforcement learning (RL) agents. However, a review of how saliency maps are used in practice indicates that the derived explanations are often…

Machine Learning · Computer Science 2020-02-24 Akanksha Atrey , Kaleigh Clary , David Jensen

Adversarial training (AT) aims to improve the robustness of deep learning models by mixing clean data and adversarial examples (AEs). Most existing AT approaches can be grouped into restricted and unrestricted approaches. Restricted AT…

Machine Learning · Computer Science 2020-04-14 Haidong Xie , Xueshuang Xiang , Naijin Liu , Bin Dong

Adversarial training (AT) refers to integrating adversarial examples -- inputs altered with imperceptible perturbations that can significantly impact model predictions -- into the training process. Recent studies have demonstrated the…

Machine Learning · Computer Science 2024-10-22 Mengnan Zhao , Lihe Zhang , Jingwen Ye , Huchuan Lu , Baocai Yin , Xinchao Wang

Adversarial training has been shown as an effective approach to improve the robustness of image classifiers against white-box attacks. However, its effectiveness against black-box attacks is more nuanced. In this work, we demonstrate that…

Machine Learning · Computer Science 2021-07-27 Ali Rahmati , Seyed-Mohsen Moosavi-Dezfooli , Huaiyu Dai

We demonstrate, theoretically and empirically, that adversarial robustness can significantly benefit from semisupervised learning. Theoretically, we revisit the simple Gaussian model of Schmidt et al. that shows a sample complexity gap…

Machine Learning · Statistics 2022-01-14 Yair Carmon , Aditi Raghunathan , Ludwig Schmidt , Percy Liang , John C. Duchi

Predicting the trajectories of surrounding objects is a critical task for self-driving vehicles and many other autonomous systems. Recent works demonstrate that adversarial attacks on trajectory prediction, where small crafted perturbations…

Machine Learning · Computer Science 2023-03-22 Ruochen Jiao , Xiangguo Liu , Takami Sato , Qi Alfred Chen , Qi Zhu

Adversarial examples reveal critical vulnerabilities in deep neural networks by exploiting their sensitivity to imperceptible input perturbations. While adversarial training remains the predominant defense strategy, it often incurs…

Machine Learning · Computer Science 2025-11-04 Longwei Wang , Ifrat Ikhtear Uddin , KC Santosh , Chaowei Zhang , Xiao Qin , Yang Zhou

Adversarial training serves as one of the most popular and effective methods to defend against adversarial perturbations. However, most defense mechanisms only consider a single type of perturbation while various attack methods might be…

Computer Vision and Pattern Recognition · Computer Science 2023-09-29 Huihui Gong , Minjing Dong , Siqi Ma , Seyit Camtepe , Surya Nepal , Chang Xu

We study the model robustness against adversarial examples, referred to as small perturbed input data that may however fool many state-of-the-art deep learning models. Unlike previous research, we establish a novel theory addressing the…

Machine Learning · Computer Science 2020-06-11 Shufei Zhang , Kaizhu Huang , Zenglin Xu

The classification decisions of neural networks can be misled by small imperceptible perturbations. This work aims to explain the misled classifications using saliency methods. The idea behind saliency methods is to explain the…

Computer Vision and Pattern Recognition · Computer Science 2019-10-22 Jindong Gu , Volker Tresp

Adversarial training and its variants have become de facto standards for learning robust deep neural networks. In this paper, we explore the landscape around adversarial training in a bid to uncover its limits. We systematically study the…

Machine Learning · Statistics 2021-03-31 Sven Gowal , Chongli Qin , Jonathan Uesato , Timothy Mann , Pushmeet Kohli

Despite their promising performance across various natural language processing (NLP) tasks, current NLP systems are vulnerable to textual adversarial attacks. To defend against these attacks, most existing methods apply adversarial training…

Computation and Language · Computer Science 2023-07-06 Junjie Wu , Dit-Yan Yeung

In some medical imaging tasks and other settings where only small parts of the image are informative for the classification task, traditional CNNs can sometimes struggle to generalise. Manually annotated Regions of Interest (ROI) are…

Image and Video Processing · Electrical Eng. & Systems 2023-08-15 Alessandro Fontanella , Antreas Antoniou , Wenwen Li , Joanna Wardlaw , Grant Mair , Emanuele Trucco , Amos Storkey

Adversarial training has been demonstrated to be one of the most effective remedies for defending adversarial examples, yet it often suffers from the huge robustness generalization gap on unseen testing adversaries, deemed as the…

Machine Learning · Computer Science 2023-03-13 Aishan Liu , Shiyu Tang , Siyuan Liang , Ruihao Gong , Boxi Wu , Xianglong Liu , Dacheng Tao

Gradient-based saliency maps have been widely used to explain the decisions of deep neural network classifiers. However, standard gradient-based interpretation maps, including the simple gradient and integrated gradient algorithms, often…

Computer Vision and Pattern Recognition · Computer Science 2024-04-09 Shizhan Gong , Qi Dou , Farzan Farnia

Neural networks are vulnerable to adversarial attacks: adding well-crafted, imperceptible perturbations to their input can modify their output. Adversarial training is one of the most effective approaches in training robust models against…

Machine Learning · Computer Science 2022-07-20 Hadi M. Dolatabadi , Sarah Erfani , Christopher Leckie

With their increase in performance, neural network architectures also become more complex, necessitating explainability. Therefore, many new and improved methods are currently emerging, which often generate so-called saliency maps in order…

Machine Learning · Computer Science 2024-12-24 Leonid Schwenke , Martin Atzmueller

Adversarial training is a method for enhancing neural networks to improve the robustness against adversarial examples. Besides the security concerns of potential adversarial examples, adversarial training can also improve the generalization…

Machine Learning · Computer Science 2022-12-21 Zhiyuan Zhang , Wei Li , Ruihan Bao , Keiko Harimoto , Yunfang Wu , Xu Sun
‹ Prev 1 3 4 5 6 7 10 Next ›