English
Related papers

Related papers: (De)Randomized Smoothing for Certifiable Defense a…

200 papers

Adversarial patch attacks are an emerging security threat for real world deep learning applications. We present Demasked Smoothing, the first approach (up to our knowledge) to certify the robustness of semantic segmentation models against…

Computer Vision and Pattern Recognition · Computer Science 2023-02-22 Maksym Yatsura , Kaspar Sakmann , N. Grace Hua , Matthias Hein , Jan Hendrik Metzen

Deep learning-based malware detection systems are vulnerable to adversarial EXEmples - carefully-crafted malicious programs that evade detection with minimal perturbation. As such, the community is dedicating effort to develop mechanisms to…

Cryptography and Security · Computer Science 2024-05-02 Daniel Gibert , Luca Demetrio , Giulio Zizzo , Quan Le , Jordi Planes , Battista Biggio

The adversarial patch attack against image classification models aims to inject adversarially crafted pixels within a restricted image region (i.e., a patch) for inducing model misclassification. This attack can be realized in the physical…

Computer Vision and Pattern Recognition · Computer Science 2022-04-12 Chong Xiang , Saeed Mahloujifar , Prateek Mittal

Adversarial patch attacks that craft the pixels in a confined region of the input images show their powerful attack effectiveness in physical environments even with noises or deformations. Existing certified defenses towards adversarial…

Computer Vision and Pattern Recognition · Computer Science 2021-11-05 Husheng Han , Kaidi Xu , Xing Hu , Xiaobing Chen , Ling Liang , Zidong Du , Qi Guo , Yanzhi Wang , Yunji Chen

Adversarial patch attacks are among one of the most practical threat models against real-world computer vision systems. This paper studies certified and empirical defenses against patch attacks. We begin with a set of experiments showing…

Cryptography and Security · Computer Science 2020-09-28 Ping-Yeh Chiang , Renkun Ni , Ahmed Abdelkader , Chen Zhu , Christoph Studer , Tom Goldstein

Localized adversarial patches aim to induce misclassification in machine learning models by arbitrarily modifying pixels within a restricted region of an image. Such attacks can be realized in the physical world by attaching the adversarial…

Computer Vision and Pattern Recognition · Computer Science 2021-04-01 Chong Xiang , Arjun Nitin Bhagoji , Vikash Sehwag , Prateek Mittal

Adversarial patch attacks inject localized perturbations into images to mislead deep vision models. These attacks can be physically deployed, posing serious risks to real-world applications. In this paper, we propose CertMask, a certifiably…

Computer Vision and Pattern Recognition · Computer Science 2025-11-14 Xuntao Lyu , Ching-Chi Lin , Abdullah Al Arafat , Georg von der Brüggen , Jian-Jia Chen , Zhishan Guo

Recently, techniques have been developed to provably guarantee the robustness of a classifier to adversarial perturbations of bounded L_1 and L_2 magnitudes by using randomized smoothing: the robust classification is a consensus of base…

Machine Learning · Computer Science 2019-11-22 Alexander Levine , Soheil Feizi

In the last couple of years, several adversarial attack methods based on different threat models have been proposed for the image classification problem. Most existing defenses consider additive threat models in which sample perturbations…

Machine Learning · Computer Science 2019-10-25 Alexander Levine , Soheil Feizi

Certified patch defenses can guarantee robustness of an image classifier to arbitrary changes within a bounded contiguous region. But, currently, this robustness comes at a cost of degraded standard accuracies and slower inference times. We…

Computer Vision and Pattern Recognition · Computer Science 2021-10-18 Hadi Salman , Saachi Jain , Eric Wong , Aleksander Mądry

Deep learning image classification is vulnerable to adversarial attack, even if the attacker changes just a small patch of the image. We propose a defense against patch attacks based on partially occluding the image around each candidate…

Machine Learning · Computer Science 2020-04-30 Michael McCoyd , Won Park , Steven Chen , Neil Shah , Ryan Roggenkemper , Minjune Hwang , Jason Xinyu Liu , David Wagner

Patch robustness certification is an emerging kind of defense technique against adversarial patch attacks with provable guarantees. There are two research lines: certified recovery and certified detection. They aim to label malicious…

Software Engineering · Computer Science 2024-05-14 Qilin Zhou , Zhengyuan Wei , Haipeng Wang , Bo Jiang , W. K. Chan

Adversarial patches pose a realistic threat model for physical world attacks on autonomous systems via their perception component. Autonomous systems in safety-critical domains such as automated driving should thus contain a fail-safe…

Machine Learning · Computer Science 2021-02-09 Jan Hendrik Metzen , Maksym Yatsura

We extend randomized smoothing to cover parameterized transformations (e.g., rotations, translations) and certify robustness in the parameter space (e.g., rotation angle). This is particularly challenging as interpolation and rounding…

Machine Learning · Computer Science 2021-08-26 Marc Fischer , Maximilian Baader , Martin Vechev

An adversarial patch can arbitrarily manipulate image pixels within a restricted region to induce model misclassification. The threat of this localized attack has gained significant attention because the adversary can mount a…

Computer Vision and Pattern Recognition · Computer Science 2021-04-27 Chong Xiang , Prateek Mittal

The adversarial patch attack aims to fool image classifiers within a bounded, contiguous region of arbitrary changes, posing a real threat to computer vision systems (e.g., autonomous driving, content moderation, biometric authentication,…

Computer Vision and Pattern Recognition · Computer Science 2023-05-19 Di Yang , Yihao Huang , Qing Guo , Felix Juefei-Xu , Ming Hu , Yang Liu , Geguang Pu

Deep learning techniques have enabled vast improvements in computer vision technologies. Nevertheless, these models are vulnerable to adversarial patch attacks which catastrophically impair performance. The physically realizable nature of…

Cryptography and Security · Computer Science 2025-06-02 Dennis Jacob , Chong Xiang , Prateek Mittal

Randomized smoothing is the dominant standard for provable defenses against adversarial examples. Nevertheless, this method has recently been proven to suffer from important information theoretic limitations. In this paper, we argue that…

Machine Learning · Computer Science 2022-06-06 Raphael Ettedgui , Alexandre Araujo , Rafael Pinot , Yann Chevaleyre , Jamal Atif

Backdoor attack is a severe security threat to deep neural networks (DNNs). We envision that, like adversarial examples, there will be a cat-and-mouse game for backdoor attacks, i.e., new empirical defenses are developed to defend against…

Cryptography and Security · Computer Science 2020-07-21 Binghui Wang , Xiaoyu Cao , Jinyuan jia , Neil Zhenqiang Gong

Implicit models such as Deep Equilibrium Models (DEQs) have emerged as promising alternative approaches for building deep neural networks. Their certified robustness has gained increasing research attention due to security concerns.…

Machine Learning · Computer Science 2024-11-05 Weizhi Gao , Zhichao Hou , Han Xu , Xiaorui Liu
‹ Prev 1 2 3 10 Next ›