English
Related papers

Related papers: PatchCleanser: Certifiably Robust Defense against …

200 papers

Physical adversarial attacks threaten to fool object detection systems, but reproducible research on the real-world effectiveness of physical patches and how to defend against them requires a publicly available benchmark dataset. We present…

Computer Vision and Pattern Recognition · Computer Science 2023-07-21 Anneliese Braunegg , Amartya Chakraborty , Michael Krumdick , Nicole Lape , Sara Leary , Keith Manville , Elizabeth Merkhofer , Laura Strickhart , Matthew Walmer

The literature on adversarial attacks in computer vision typically focuses on pixel-level perturbations. These tend to be very difficult to interpret. Recent work that manipulates the latent representations of image generators to create…

Machine Learning · Computer Science 2023-09-12 Stephen Casper , Max Nadeau , Dylan Hadfield-Menell , Gabriel Kreiman

Deep learning vision systems are increasingly deployed in safety-critical domains such as healthcare, yet they remain vulnerable to small adversarial patches that can trigger misclassifications. Most existing defenses assume a single patch…

Computer Vision and Pattern Recognition · Computer Science 2025-11-12 Aja Khanal , Ahmed Faid , Apurva Narayan

Adversarial attacks pose a significant threat to the robustness and reliability of machine learning systems, particularly in computer vision applications. This study investigates the performance of adversarial patches for the YOLO object…

Computer Vision and Pattern Recognition · Computer Science 2024-11-27 Jakob Shack , Katarina Petrovic , Olga Saukh

Person detection has attracted great attention in the computer vision area and is an imperative element in human-centric computer vision. Although the predictive performances of person detection networks have been improved dramatically,…

Computer Vision and Pattern Recognition · Computer Science 2022-11-30 Youngjoon Yu , Hong Joo Lee , Hakmin Lee , Yong Man Ro

Adversarial patch attacks threaten the reliability of modern vision models. We present PatchMap, the first spatially exhaustive benchmark of patch placement, built by evaluating over 1.5e8 forward passes on ImageNet validation images.…

Computer Vision and Pattern Recognition · Computer Science 2025-08-05 Shai Kimhi , Avi Mendlson , Moshe Kimhi

Deep neural networks have been widely used in many computer vision tasks. However, it is proved that they are susceptible to small, imperceptible perturbations added to the input. Inputs with elaborately designed perturbations that can fool…

Computer Vision and Pattern Recognition · Computer Science 2020-10-29 Yusheng Zhao , Huanqian Yan , Xingxing Wei

Face recognition is greatly improved by deep convolutional neural networks (CNNs). Recently, these face recognition models have been used for identity authentication in security sensitive applications. However, deep CNNs are vulnerable to…

Computer Vision and Pattern Recognition · Computer Science 2021-08-31 Zihao Xiao , Xianfeng Gao , Chilin Fu , Yinpeng Dong , Wei Gao , Xiaolu Zhang , Jun Zhou , Jun Zhu

Adversarial perturbations of normal images are usually imperceptible to humans, but they can seriously confuse state-of-the-art machine learning models. What makes them so special in the eyes of image classifiers? In this paper, we show…

Machine Learning · Computer Science 2018-05-22 Yang Song , Taesup Kim , Sebastian Nowozin , Stefano Ermon , Nate Kushman

Adversarial patches threaten visual AI models in the real world. The number of patches in a patch attack is variable and determines the attack's potency in a specific environment. Most existing defenses assume a single patch in the scene,…

Computer Vision and Pattern Recognition · Computer Science 2023-11-06 Abhijith Sharma , Phil Munz , Apurva Narayan

Patch robustness certification is an emerging kind of provable defense technique against adversarial patch attacks for deep learning systems. Certified detection ensures the detection of all patched harmful versions of certified samples,…

Software Engineering · Computer Science 2025-12-09 Qilin Zhou , Zhengyuan Wei , Haipeng Wang , Zhuo Wang , W. K. Chan

Adversarial attacks pose a significant challenge to the reliable deployment of machine learning models in EdgeAI applications, such as autonomous driving and surveillance, which rely on resource-constrained devices for real-time inference.…

Cryptography and Security · Computer Science 2026-01-05 Nandish Chattopadhyay , Abdul Basit , Amira Guesmi , Muhammad Abdullah Hanif , Bassem Ouni , Muhammad Shafique

Deep neural networks, although shown to be a successful class of machine learning algorithms, are known to be extremely unstable to adversarial perturbations. Improving the robustness of neural networks against these attacks is important,…

Computer Vision and Pattern Recognition · Computer Science 2019-04-29 Seyed-Mohsen Moosavi-Dezfooli , Ashish Shrivastava , Oncel Tuzel

We study black-box adversarial attacks for image classifiers in a constrained threat model, where adversaries can only modify a small fraction of pixels in the form of scratches on an image. We show that it is possible for adversaries to…

Neural and Evolutionary Computing · Computer Science 2020-08-07 Malhar Jere , Loris Rossi , Briland Hitaj , Gabriela Ciocarlie , Giacomo Boracchi , Farinaz Koushanfar

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

Deep neural networks are successfully used in various applications, but show their vulnerability to adversarial examples. With the development of adversarial patches, the feasibility of attacks in physical scenes increases, and the defenses…

Computer Vision and Pattern Recognition · Computer Science 2023-07-27 Junwen Chen , Xingxing Wei

The widespread adoption of computer vision systems has underscored their susceptibility to adversarial attacks, particularly adversarial patch attacks on object detectors. This study evaluates defense mechanisms for the YOLOv5 model against…

Computer Vision and Pattern Recognition · Computer Science 2025-06-30 Roie Kazoom , Raz Birman , Ofer Hadar

This chapter introduces the concept of adversarial attacks on image classification models built on convolutional neural networks (CNN). CNNs are very popular deep-learning models which are used in image classification tasks. However, very…

Computer Vision and Pattern Recognition · Computer Science 2023-07-06 Jaydip Sen , Subhasis Dasgupta

The vulnerabilities of deep neural networks against singularities have raised serious concerns regarding their deployment in the physical world. One of the most prominent and impactful physical-world adversarial perturbations is the…

Computer Vision and Pattern Recognition · Computer Science 2026-04-30 Vishesh Kumar , Akshay Agarwal

Machine-learning architectures, such as Convolutional Neural Networks (CNNs) are vulnerable to adversarial attacks: inputs crafted carefully to force the system output to a wrong label. Since machine-learning is being deployed in…

Cryptography and Security · Computer Science 2022-11-03 Amira Guesmi , Ihsen Alouani , Khaled N. Khasawneh , Mouna Baklouti , Tarek Frikha , Mohamed Abid , Nael Abu-Ghazaleh