Patch Attack

Patch attacks involve strategically placing small, visually inconspicuous adversarial patches on images or videos to fool deep learning models, primarily in computer vision applications like autonomous driving and object recognition. Current research focuses on developing robust defenses, employing techniques like diffusion models, image inpainting, and entropy-based analysis to detect and mitigate these attacks, often within a certified robustness framework. This area is crucial for ensuring the safety and reliability of AI systems deployed in real-world scenarios, particularly those with safety-critical implications. The development of effective defenses against patch attacks is a significant challenge driving ongoing research and innovation in adversarial machine learning.

Papers

September 14, 2024

Real-world Adversarial Defense against Patch Attacks based on Diffusion Model
Xingxing Wei, Caixin Kang, Yinpeng Dong, Zhengyi Wang, Shouwei Ruan, Yubo Chen, Hang Su
Diffusion Model Anomaly Detection Adversarial Patch Adversarial Patch Attack Patch Attack

September 6, 2024

Secure Traffic Sign Recognition: An Attention-Enabled Universal Image Inpainting Mechanism against Light Patch Attacks
Hangcheng Cao, Longzhi Yuan, Guowen Xu, Ziyang He, Zhengru Fang, Yuguang Fang
Adversarial Patch Functional Mechanism Traffic Sign Recognition Patch Attack Adversarial Infrared Patch Based Attack

August 27, 2024

Adversarial Manhole: Challenging Monocular Depth Estimation and Semantic Segmentation Models with Patch Attack
Naufal Suryanto, Andro Aprila Adiputra, Ahmada Yusril Kadiptya, Yongsu Kim, Howon Kim
Semantic Segmentation Monocular Depth Estimation Semantic Segmentation Model Depth Map Adversarial Patch Adversarial Scenario Patch Attack Adversarial Backdoor

May 13, 2024

CrossCert: A Cross-Checking Detection Approach to Patch Robustness Certification for Deep Learning Models
Qilin Zhou, Zhengyuan Wei, Haipeng Wang, Bo Jiang, W. K. Chan
Deep Learning Model Accurate Detection Adversarial Patch Attack Robustness Certification Patch Attack

May 1, 2024

Certified Adversarial Robustness of Machine Learning-based Malware Detectors via (De)Randomized Smoothing
Daniel Gibert, Luca Demetrio, Giulio Zizzo, Quan Le, Jordi Planes, Battista Biggio
Malware Detection Adversarial Patch Adversarial Text Smoothing Factor Patch Attack Insertion Based

November 2, 2023

Assist Is Just as Important as the Goal: Image Resurfacing to Aid Model's Robust Prediction
Abhijith Sharma, Phil Munz, Apurva Narayan
Full Model Adversarial Patch Pseudo Goal Robust Prediction Patch Attack Adversarial Region

September 4, 2023

Adv3D: Generating 3D Adversarial Examples in Driving Scenarios with NeRF
Leheng Li, Qing Lian, Ying-Cong Chen
Adversarial Example NeRF SLAM Multi Scenario Patch Attack 3D Adversarial

July 5, 2023

Adversarial Attacks on Image Classification Models: FGSM and Patch Attacks and their Impact
Jaydip Sen, Subhasis Dasgupta
Convolutional Neural Network Adversarial Attack Global Impact Pre Trained Convolutional Neural Network Adversarial Patch Attack Image Classification Model Patch Attack Fast Gradient Sign Method

July 2, 2023

Query-Efficient Decision-based Black-Box Patch Attack
Zhaoyu Chen, Bo Li, Shuang Wu, Shouhong Ding, Wenqiang Zhang
Imperceptible Adversarial Perturbation Patch Attack

June 15, 2023

DIFFender: Diffusion-Based Adversarial Defense against Patch Attacks
Caixin Kang, Yinpeng Dong, Zhengyi Wang, Shouwei Ruan, Yubo Chen, Hang Su, Xingxing Wei
Adversarial Attack Adversarial Patch Adversarial DEfense Defense Method Patch Attack Adversarial Region

April 20, 2023

Jedi: Entropy-based Localization and Removal of Adversarial Patches
Bilel Tarchoun, Anouar Ben Khalifa, Mohamed Ali Mahjoub, Nael Abu-Ghazaleh, Ihsen Alouani
Adversarial Patch Image Patch Active Removal Patch Attack Physical Adversarial Patch

March 30, 2023

Understanding the Robustness of 3D Object Detection with Bird's-Eye-View Representations in Autonomous Driving
Zijian Zhu, Yichi Zhang, Hai Chen, Yinpeng Dong, Shu Zhao, Wenbo Ding, Jiachen Zhong, Shibao Zheng
Autonomous Driving Native Robustness 3D Object Detection Bird'S Eye View 3D Detector Bird'S Eye View Map Segmentation Patch Attack Camera LiDAR Fusion Model

March 21, 2023

Efficient Decision-based Black-box Patch Attacks on Video Recognition
Kaixun Jiang, Zhaoyu Chen, Hao Huang, Jiafeng Wang, Dingkang Yang, Bo Li, Yan Wang, Wenqiang Zhang
High Efficiency Adversarial Patch Video Recognition Differential Evolution Patch Attack Decision Based

February 13, 2023

Threatening Patch Attacks on Object Detection in Optical Remote Sensing Images
Xuxiang Sun, Gong Cheng, Lei Pei, Hongda Li, Junwei Han
Bounding Box Optical Remote Sensing Image Patch Attack Patch Selection

December 12, 2022

REAP: A Large-Scale Realistic Adversarial Patch Benchmark
Nabeel Hingun, Chawin Sitawarin, Jerry Li, David Wagner
Adversarial Perturbation Adversarial Patch Renewable Energy Adversarial Patch Attack Patch Attack

September 13, 2022

Certified Defences Against Adversarial Patch Attacks on Semantic Segmentation
Maksym Yatsura, Kaspar Sakmann, N. Grace Hua, Matthias Hein, Jan Hendrik Metzen
Semantic Segmentation Segmentation Model Semantic Segmentation Model Adversarial Patch Attack Patch Attack Certified Defense

July 5, 2022

PatchZero: Defending against Adversarial Patch Attacks by Detecting and Zeroing the Patch
Ke Xu, Yao Xiao, Zhaoheng Zheng, Kaijie Cai, Ram Nevatia
Data Detection Adversarial Patch Adversarial Patch Attack Single Simple Patch Patch Attack

June 16, 2022

Adversarial Patch Attacks and Defences in Vision-Based Tasks: A Survey
Abhijith Sharma, Yijun Bian, Phil Munz, Apurva Narayan
Timely Survey Adversarial Attack Vision Task Adversarial Patch Adversarial Patch Attack Patch Attack Primitive Based Adversarial Training

May 18, 2022

Constraining the Attack Space of Machine Learning Models with Distribution Clamping Preprocessing
Ryan Feng, Somesh Jha, Atul Prakash
Native Robustness Machine Learning Model Outlier Detection Car Learning to Act Preprocessing Method Patch Attack Space Attack