Adversarial Patch

Adversarial patches are small, carefully designed images that can fool deep learning models, causing misclassifications or incorrect predictions in computer vision tasks. Current research focuses on developing increasingly realistic and effective patches, often leveraging diffusion models and optimization techniques to create patches that are both potent and visually inconspicuous, targeting various applications like autonomous driving and traffic sign recognition. This research is crucial for understanding and mitigating vulnerabilities in AI systems, particularly in safety-critical applications where reliable performance is paramount. The development of robust defenses against these attacks is a parallel and equally important area of investigation.

Papers

October 7, 2022

Multi-Frequency-Aware Patch Adversarial Learning for Neural Point Cloud Rendering
Jay Karhade, Haiyue Zhu, Ka-Shing Chung, Rajesh Tripathy, Wei Lin, Marcelo H. Ang
Point Cloud Adversarial Learning Adversarial Patch Patch Level Object Centric Voxelization

September 27, 2022

Suppress with a Patch: Revisiting Universal Adversarial Patch Attacks against Object Detection
Svetlana Pavlitskaya, Jonas Hendl, Sebastian Kleim, Leopold Müller, Fabian Wylczoch, J. Marius Zöllner
Adversarial Patch Single Simple Patch Copy Suppression Patch Generation Patch Selection

August 19, 2022

Real-Time Robust Video Object Detection System Against Physical-World Adversarial Attacks
Husheng Han, Xing Hu, Kaidi Xu, Pucheng Dang, Ying Wang, Yongwei Zhao, Zidong Du, Qi Guo, Yanzhi Yang, Tianshi Chen
Adversarial Attack Adversarial Patch Video Object Detection Adversarial Patch Attack Adversarial Region

July 24, 2022

PCA: Semi-supervised Segmentation with Patch Confidence Adversarial Training
Zihang Xu, Zhenghua Xu, Shuo Zhang, Thomas Lukasiewicz
Semi Supervised Learning Adversarial Patch Semi Supervised Segmentation Semi Supervised Adversarial

July 15, 2022

Feasibility of Inconspicuous GAN-generated Adversarial Patches against Object Detection
Svetlana Pavlitskaya, Bianca-Marina Codău, J. Marius Zöllner
Generative Adversarial Network Adversarial Patch Task Feasibility Image Patch Digital STEALTH Metric Adversarial Patch Generation

July 11, 2022

Physical Attack on Monocular Depth Estimation with Optimal Adversarial Patches
Zhiyuan Cheng, James Liang, Hongjun Choi, Guanhong Tao, Zhiwen Cao, Dongfang Liu, Xiangyu Zhang
Monocular Depth Estimation Vision Based Adversarial Patch Physical Adversarial Patch Adversarial Object Physical Attack

July 6, 2022

The Weaknesses of Adversarial Camouflage in Overhead Imagery
Adam Van Etten
Adversarial Attack Object Detector Adversarial Patch Object Detection Algorithm Physical Weakness Adversarial CAmouflage Overhead Imagery

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 25, 2022

Empirical Evaluation of Physical Adversarial Patch Attacks Against Overhead Object Detection Models
Gavin S. Hartnett, Li Ang Zhang, Caolionn O'Connell, Andrew J. Lohn, Jair Aguirre
Adversarial Example Object Detection Model Adversarial Patch Empirical Evaluation Adversarial Patch Attack Physical Adversarial Patch Overhead Object Detection

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 21, 2022

On the Feasibility and Generality of Patch-based Adversarial Attacks on Semantic Segmentation Problems
Soma Kontar, Andras Horvath
Deep Neural Network Adversarial Attack Receptive Field Segmentation Network Adversarial Patch Task Feasibility Semantic Segmentation Problem Patch Based Attack

May 10, 2022

Using Frequency Attention to Make Adversarial Patch Powerful Against Person Detector
Xiaochun Lei, Chang Lu, Zetao Jiang, Zhaoting Gong, Xiang Cai, Linjun Lu
Adversarial Attack Attention Module Adversarial Patch Person Detector Frequency Attention

March 25, 2022

Give Me Your Attention: Dot-Product Attention Considered Harmful for Adversarial Patch Robustness
Giulio Lovisotto, Nicole Finnie, Mauricio Munoz, Chaithanya Kumar Mummadi, Jan Hendrik Metzen
Human Attention Adversarial Patch Adversarial Patch Attack Adversarial Objective Dot Product Attention

March 7, 2022

February 17, 2022

Developing Imperceptible Adversarial Patches to Camouflage Military Assets From Computer Vision Enabled Technologies
Chris Wise, Jo Plested
Adversarial Attack Computer Vision Adversarial Patch Technology Information Data False Positive Military Application Imperceptible Pattern Camouflage Image

February 3, 2022

ObjectSeeker: Certifiably Robust Object Detection against Patch Hiding Attacks via Patch-agnostic Masking
Chong Xiang, Alexander Valtchanov, Saeed Mahloujifar, Prateek Mittal
Object Detector Adversarial Patch Robust Object Detection Patch Masking Object Search Physical Adversarial Patch Patch Based Attack

January 17, 2022

Fooling the Eyes of Autonomous Vehicles: Robust Physical Adversarial Examples Against Traffic Sign Recognition Systems
Wei Jia, Zhaojun Lu, Haichun Zhang, Zhenglin Liu, Jie Wang, Gang Qu
Autonomous Vehicle Adversarial Example DNN Model Adversarial Patch Character Eye Traffic Sign Recognition Physical Adversarial

January 5, 2022

On the Real-World Adversarial Robustness of Real-Time Semantic Segmentation Models for Autonomous Driving
Giulio Rossolini, Federico Nesti, Gianluca D'Amico, Saasha Nair, Alessandro Biondi, Giorgio Buttazzo
Autonomous Driving Adversarial Example Adversarial Patch Real Time Semantic Segmentation Adversarial Influence

December 8, 2021

Segment and Complete: Defending Object Detectors against Adversarial Patch Attacks with Robust Patch Detection
Jiang Liu, Alexander Levine, Chun Pong Lau, Rama Chellappa, Soheil Feizi
Object Detector Adversarial Patch Patch Based Well Defined Segment Adversarial Patch Attack

Adversarial Patch

Papers

Multi-Frequency-Aware Patch Adversarial Learning for Neural Point Cloud Rendering

Suppress with a Patch: Revisiting Universal Adversarial Patch Attacks against Object Detection

Real-Time Robust Video Object Detection System Against Physical-World Adversarial Attacks

PCA: Semi-supervised Segmentation with Patch Confidence Adversarial Training

Feasibility of Inconspicuous GAN-generated Adversarial Patches against Object Detection

Physical Attack on Monocular Depth Estimation with Optimal Adversarial Patches

The Weaknesses of Adversarial Camouflage in Overhead Imagery

PatchZero: Defending against Adversarial Patch Attacks by Detecting and Zeroing the Patch

Empirical Evaluation of Physical Adversarial Patch Attacks Against Overhead Object Detection Models

Adversarial Patch Attacks and Defences in Vision-Based Tasks: A Survey

On the Feasibility and Generality of Patch-based Adversarial Attacks on Semantic Segmentation Problems

Using Frequency Attention to Make Adversarial Patch Powerful Against Person Detector

Give Me Your Attention: Dot-Product Attention Considered Harmful for Adversarial Patch Robustness

ImageNet-Patch: A Dataset for Benchmarking Machine Learning Robustness against Adversarial Patches

Adversarial Texture for Fooling Person Detectors in the Physical World

Developing Imperceptible Adversarial Patches to Camouflage Military Assets From Computer Vision Enabled Technologies

ObjectSeeker: Certifiably Robust Object Detection against Patch Hiding Attacks via Patch-agnostic Masking

Fooling the Eyes of Autonomous Vehicles: Robust Physical Adversarial Examples Against Traffic Sign Recognition Systems

On the Real-World Adversarial Robustness of Real-Time Semantic Segmentation Models for Autonomous Driving

Segment and Complete: Defending Object Detectors against Adversarial Patch Attacks with Robust Patch Detection