English
Related papers

Related papers: Certified Defences Against Adversarial Patch Attac…

200 papers

Deep neural network-based image classifications are vulnerable to adversarial perturbations. The image classifications can be easily fooled by adding artificial small and imperceptible perturbations to input images. As one of the most…

Computer Vision and Pattern Recognition · Computer Science 2023-08-16 Jindong Gu , Hengshuang Zhao , Volker Tresp , Philip Torr

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

Recently, self-supervised learning (SSL) was shown to be vulnerable to patch-based data poisoning backdoor attacks. It was shown that an adversary can poison a small part of the unlabeled data so that when a victim trains an SSL model on…

Computer Vision and Pattern Recognition · Computer Science 2023-04-05 Ajinkya Tejankar , Maziar Sanjabi , Qifan Wang , Sinong Wang , Hamed Firooz , Hamed Pirsiavash , Liang Tan

Certified defenses such as randomized smoothing have shown promise towards building reliable machine learning systems against $\ell_p$-norm bounded attacks. However, existing methods are insufficient or unable to provably defend against…

Machine Learning · Computer Science 2022-06-30 Zhongkai Hao , Chengyang Ying , Yinpeng Dong , Hang Su , Jun Zhu , Jian Song

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 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

We present a new certification method for image and point cloud segmentation based on randomized smoothing. The method leverages a novel scalable algorithm for prediction and certification that correctly accounts for multiple testing,…

Machine Learning · Computer Science 2022-07-28 Marc Fischer , Maximilian Baader , Martin Vechev

Deep learning interpretation is essential to explain the reasoning behind model predictions. Understanding the robustness of interpretation methods is important especially in sensitive domains such as medical applications since…

Machine Learning · Computer Science 2019-10-21 Alexander Levine , Sahil Singla , Soheil Feizi

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

Object detectors, which are widely deployed in security-critical systems such as autonomous vehicles, have been found vulnerable to patch hiding attacks. An attacker can use a single physically-realizable adversarial patch to make the…

Computer Vision and Pattern Recognition · Computer Science 2023-01-02 Chong Xiang , Alexander Valtchanov , Saeed Mahloujifar , Prateek Mittal

Nowadays, Deep learning techniques show dramatic performance on computer vision area, and they even outperform human. But it is also vulnerable to some small perturbation called an adversarial attack. This is a problem combined with the…

Computer Vision and Pattern Recognition · Computer Science 2020-04-08 Seungju Cho , Tae Joon Jun , Byungsoo Oh , Daeyoung Kim

As ML models are increasingly deployed in critical applications, robustness against adversarial perturbations is crucial. While numerous defenses have been proposed to counter such attacks, they typically assume that all adversarial…

Machine Learning · Computer Science 2025-06-11 Yuan Xin , Dingfan Chen , Michael Backes , Xiao Zhang

Certifiably robust defenses against adversarial patches for image classifiers ensure correct prediction against any changes to a constrained neighborhood of pixels. PatchCleanser arXiv:2108.09135 [cs.CV], the state-of-the-art certified…

Computer Vision and Pattern Recognition · Computer Science 2023-06-23 Aniruddha Saha , Shuhua Yu , Arash Norouzzadeh , Wan-Yi Lin , Chaithanya Kumar Mummadi

Object detection is fundamental to various real-world applications, such as security monitoring and surveillance video analysis. Despite their advancements, state-of-the-art object detectors are still vulnerable to adversarial patch…

Computer Vision and Pattern Recognition · Computer Science 2026-03-24 Jin Ma , Mohammed Aldeen , Christopher Salas , Feng Luo , Mashrur Chowdhury , Mert Pesé , Long Cheng

We present a method for provably defending any pretrained image classifier against $\ell_p$ adversarial attacks. This method, for instance, allows public vision API providers and users to seamlessly convert pretrained non-robust…

Machine Learning · Computer Science 2020-09-22 Hadi Salman , Mingjie Sun , Greg Yang , Ashish Kapoor , J. Zico Kolter

While Automatic Speech Recognition has been shown to be vulnerable to adversarial attacks, defenses against these attacks are still lagging. Existing, naive defenses can be partially broken with an adaptive attack. In classification tasks,…

Computation and Language · Computer Science 2022-01-12 Raphael Olivier , Bhiksha Raj

Deep learning has substantially boosted the performance of Monocular Depth Estimation (MDE), a critical component in fully vision-based autonomous driving (AD) systems (e.g., Tesla and Toyota). In this work, we develop an attack against…

Computer Vision and Pattern Recognition · Computer Science 2022-07-12 Zhiyuan Cheng , James Liang , Hongjun Choi , Guanhong Tao , Zhiwen Cao , Dongfang Liu , Xiangyu Zhang

In the ever-evolving adversarial machine learning landscape, developing effective defenses against patch attacks has become a critical challenge, necessitating reliable solutions to safeguard real-world AI systems. Although diffusion models…

Computer Vision and Pattern Recognition · Computer Science 2024-11-15 Jia Fu , Xiao Zhang , Sepideh Pashami , Fatemeh Rahimian , Anders Holst

Machine learning models have demonstrated remarkable success across diverse domains but remain vulnerable to adversarial attacks. Empirical defense mechanisms often fail, as new attacks constantly emerge, rendering existing defenses…

Machine Learning · Computer Science 2024-10-25 Anupriya Kumari , Devansh Bhardwaj , Sukrit Jindal

Recently, few certified defense methods have been developed to provably guarantee the robustness of a text classifier to adversarial synonym substitutions. However, all existing certified defense methods assume that the defenders are…

Computation and Language · Computer Science 2021-07-27 Jiehang Zeng , Xiaoqing Zheng , Jianhan Xu , Linyang Li , Liping Yuan , Xuanjing Huang