English
Related papers

Related papers: Cross-Input Certified Training for Universal Pertu…

200 papers

We present an algorithm for computing class-specific universal adversarial perturbations for deep neural networks. Such perturbations can induce misclassification in a large fraction of images of a specific class. Unlike previous methods…

Machine Learning · Computer Science 2019-12-03 Tejus Gupta , Abhishek Sinha , Nupur Kumari , Mayank Singh , Balaji Krishnamurthy

We propose a novel technique to make neural network robust to adversarial examples using a generative adversarial network. We alternately train both classifier and generator networks. The generator network generates an adversarial…

Machine Learning · Computer Science 2023-07-06 Hyeungill Lee , Sungyeob Han , Jungwoo Lee

The existence of adversarial examples points to a basic weakness of deep neural networks. One of the most effective defenses against such examples, adversarial training, entails training models with some degree of robustness, usually at the…

Machine Learning · Computer Science 2023-10-05 Matan Levi , Aryeh Kontorovich

To deflect adversarial attacks, a range of "certified" classifiers have been proposed. In addition to labeling an image, certified classifiers produce (when possible) a certificate guaranteeing that the input image is not an…

Machine Learning · Computer Science 2020-03-20 Amin Ghiasi , Ali Shafahi , Tom Goldstein

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

Research on adversarial robustness is primarily focused on image and text data. Yet, many scenarios in which lack of robustness can result in serious risks, such as fraud detection, medical diagnosis, or recommender systems often do not…

Machine Learning · Computer Science 2023-12-14 Klim Kireev , Maksym Andriushchenko , Carmela Troncoso , Nicolas Flammarion

Recently, deep learning has been applied to many security-sensitive applications, such as facial authentication. The existence of adversarial examples hinders such applications. The state-of-the-art result on defense shows that adversarial…

Machine Learning · Computer Science 2018-05-15 Qi-Zhi Cai , Min Du , Chang Liu , Dawn Song

On the one hand, there has been considerable progress on neural network verification in recent years, which makes certifying neural networks a possibility. On the other hand, neural networks in practice are often re-trained over time to…

Machine Learning · Computer Science 2024-07-10 Long H. Pham , Jun Sun

Vision-language pre-trained (VLP) models have been the foundation of numerous vision-language tasks. Given their prevalence, it becomes imperative to assess their adversarial robustness, especially when deploying them in security-crucial…

Computer Vision and Pattern Recognition · Computer Science 2024-05-12 Peng-Fei Zhang , Zi Huang , Guangdong Bai

A single perturbation can pose the most natural images to be misclassified by classifiers. In black-box setting, current universal adversarial attack methods utilize substitute models to generate the perturbation, then apply the…

Computer Vision and Pattern Recognition · Computer Science 2021-01-06 Jing Wu , Mingyi Zhou , Shuaicheng Liu , Yipeng Liu , Ce Zhu

While adversarial training and its variants have shown to be the most effective algorithms to defend against adversarial attacks, their extremely slow training process makes it hard to scale to large datasets like ImageNet. The key idea of…

Machine Learning · Computer Science 2022-06-07 Zhichao Huang , Yanbo Fan , Chen Liu , Weizhong Zhang , Yong Zhang , Mathieu Salzmann , Sabine Süsstrunk , Jue Wang

Adversarial training (AT) and its variants have spearheaded progress in improving neural network robustness to adversarial perturbations and common corruptions in the last few years. Algorithm design of AT and its variants are focused on…

Machine Learning · Computer Science 2022-06-15 Kaustubh Sridhar , Souradeep Dutta , Ramneet Kaur , James Weimer , Oleg Sokolsky , Insup Lee

We focus on the robustness of neural networks for classification. To permit a fair comparison between methods to achieve robustness, we first introduce a standard based on the mensuration of a classifier's degradation. Then, we propose…

Computer Vision and Pattern Recognition · Computer Science 2021-03-23 Sadaf Gulshad , Arnold Smeulders

Adversarial training (i.e., training on adversarially perturbed input data) is a well-studied method for making neural networks robust to potential adversarial attacks during inference. However, the improved robustness does not come for…

Robotics · Computer Science 2023-01-27 Mathias Lechner , Alexander Amini , Daniela Rus , Thomas A. Henzinger

Robust training methods typically defend against specific attack types, such as Lp attacks with fixed budgets, and rarely account for the fact that defenders may encounter new attacks over time. A natural solution is to adapt the defended…

Machine Learning · Computer Science 2025-02-07 Sihui Dai , Christian Cianfarani , Arjun Bhagoji , Vikash Sehwag , Prateek Mittal

Adversarial training is a standard defense against malicious input perturbations in security-critical machine-learning systems. Its main burden is structural: before every parameter update, the current model must first be attacked to find a…

Quantum Physics · Physics 2026-03-31 Yue Wang , Guangyi He , Liepeng Zhang , Lukas Gonon , Qi Zhao

Modern deep learning based classifiers show very high accuracy on test data but this does not provide sufficient guarantees for safe deployment, especially in high-stake AI applications such as medical diagnosis. Usually, predictions are…

Machine Learning · Computer Science 2022-05-09 David Stutz , Krishnamurthy , Dvijotham , Ali Taylan Cemgil , Arnaud Doucet

Adversarial training is an effective defense method to protect classification models against adversarial attacks. However, one limitation of this approach is that it can require orders of magnitude additional training time due to high cost…

Machine Learning · Computer Science 2020-07-03 Haizhong Zheng , Ziqi Zhang , Juncheng Gu , Honglak Lee , Atul Prakash

Classical adversarial training (AT) frameworks are designed to achieve high adversarial accuracy against a single attack type, typically $\ell_\infty$ norm-bounded perturbations. Recent extensions in AT have focused on defending against the…

Machine Learning · Computer Science 2021-06-15 Ameya D. Patil , Michael Tuttle , Alexander G. Schwing , Naresh R. Shanbhag

This paper proposes a novel, abstraction-based, certified training method for robust image classifiers. Via abstraction, all perturbed images are mapped into intervals before feeding into neural networks for training. By training on…

Computer Vision and Pattern Recognition · Computer Science 2023-03-22 Zhaodi Zhang , Zhiyi Xue , Yang Chen , Si Liu , Yueling Zhang , Jing Liu , Min Zhang