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

November 29, 2023

NeRFTAP: Enhancing Transferability of Adversarial Patches on Face Recognition using Neural Radiance Fields
Xiaoliang Liu, Furao Shen, Feng Han, Jian Zhao, Changhai Nie
Adversarial Attack Neural Radiance Field Face Recognition Task Transferability Adversarial Patch UV Mapping Adversarial Face

November 20, 2023

ODDR: Outlier Detection & Dimension Reduction Based Defense Against Adversarial Patches
Nandish Chattopadhyay, Amira Guesmi, Muhammad Abdullah Hanif, Bassem Ouni, Muhammad Shafique
Adversarial Attack Adversarial Perturbation Outlier Detection Adversarial Patch Dimension Reduction Adversarial Patch Attack Patch Based Attack

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

October 26, 2023

Detection Defenses: An Empty Promise against Adversarial Patch Attacks on Optical Flow
Erik Scheurer, Jenny Schmalfuss, Alexander Lis, Andrés Bruhn
Adversarial Robustness Optical Flow Adversarial Patch Adversarial Patch Attack

October 19, 2023

PatchCURE: Improving Certifiable Robustness, Model Utility, and Computation Efficiency of Adversarial Patch Defenses
Chong Xiang, Tong Wu, Sihui Dai, Jonathan Petit, Suman Jana, Prateek Mittal
Adversarial Patch Computational Efficiency Model Improvement Adversarial Patch Attack Certifiable Robustness State of the Art Robustness Defensive Patch

October 5, 2023

Targeted Adversarial Attacks on Generalizable Neural Radiance Fields
Andras Horvath, Csaba M. Jozsa
Adversarial Attack Neural Radiance Field Adversarial Patch 3D Scene Representation Fast Adversarial Training Generalizable Neural Radiance Field

October 4, 2023

SlowFormer: Universal Adversarial Patch for Attack on Compute and Energy Efficiency of Inference Efficient Vision Transformers
KL Navaneet, Soroush Abbasi Koohpayegani, Essam Sleiman, Hamed Pirsiavash
Vision Transformer Deep Model Adversarial Patch Transformer Inference Standard Adversarial Training

September 27, 2023

Defending Against Physical Adversarial Patch Attacks on Infrared Human Detection
Lukas Strack, Futa Waseda, Huy H. Nguyen, Yinqiang Zheng, Isao Echizen
Adversarial Patch Adversarial Patch Attack Infrared Object Physical Adversarial Patch

August 14, 2023

AdvCLIP: Downstream-agnostic Adversarial Examples in Multimodal Contrastive Learning
Ziqi Zhou, Shengshan Hu, Minghui Li, Hangtao Zhang, Yechao Zhang, Hai Jin
Contrastive Learning Generative Adversarial Network Cross Modal Adversarial Patch

August 10, 2023

Generating Transferable and Stealthy Adversarial Patch via Attention-guided Adversarial Inpainting
Yanjie Li, Mingxing Duan, Xuelong Dai, Bin Xiao
Adversarial Patch Adversarial Patch Attack Refinement Network

August 6, 2023

SAAM: Stealthy Adversarial Attack on Monocular Depth Estimation
Amira Guesmi, Muhammad Abdullah Hanif, Bassem Ouni, Muhammad Shafique
Adversarial Attack Monocular Depth Estimation Adversarial Patch

August 1, 2023

Kidnapping Deep Learning-based Multirotors using Optimized Flying Adversarial Patches
Pia Hanfeld, Khaled Wahba, Marina M. -C. Höhne, Michael Bussmann, Wolfgang Hönig
Adversarial Attack Adversarial Patch Diving Deep Adversarial Multi

July 27, 2023

Unified Adversarial Patch for Visible-Infrared Cross-modal Attacks in the Physical World
Xingxing Wei, Yao Huang, Yitong Sun, Jie Yu
Adversarial Attack Adversarial Patch Physical World Modal Attack

July 26, 2023

Defending Adversarial Patches via Joint Region Localizing and Inpainting
Junwen Chen, Xingxing Wei
Adversarial Patch Adversarial Patch Attack Joint Localization

July 16, 2023

Diffusion to Confusion: Naturalistic Adversarial Patch Generation Based on Diffusion Model for Object Detector
Shuo-Yen Lin, Ernie Chu, Che-Hsien Lin, Jun-Cheng Chen, Jia-Ching Wang
Diffusion Model Object Detector Diffusion Explainer Adversarial Patch Physical Adversarial Patch Adversarial Patch Generation

July 15, 2023

Unified Adversarial Patch for Cross-modal Attacks in the Physical World
Xingxing Wei, Yao Huang, Yitong Sun, Jie Yu
Adversarial Attack Adversarial Patch Physical World Modal Attack

July 9, 2023

Random Position Adversarial Patch for Vision Transformers
Mingzhen Shao
Vision Transformer Adversarial Patch GAN Structure

June 28, 2023

Distributional Modeling for Location-Aware Adversarial Patches
Xingxing Wei, Shouwei Ruan, Yinpeng Dong, Hang Su
Adversarial Attack Adversarial Patch Distributional Model Adversarial Region

June 22, 2023

Revisiting Image Classifier Training for Improved Certified Robust Defense against Adversarial Patches
Aniruddha Saha, Shuhua Yu, Arash Norouzzadeh, Wan-Yi Lin, Chaithanya Kumar Mummadi
Adversarial Patch Image Classifier Mask Guided Masking Strategy Feature Masking Optimal Mask

June 19, 2023

Eigenpatches -- Adversarial Patches from Principal Components
Jens Bayer, Stefan Becker, David Münch, Michael Arens
Adversarial Patch White Box Evasion Attack Principal Component Eigen Portfolio

Adversarial Patch

Papers

NeRFTAP: Enhancing Transferability of Adversarial Patches on Face Recognition using Neural Radiance Fields

ODDR: Outlier Detection & Dimension Reduction Based Defense Against Adversarial Patches

Assist Is Just as Important as the Goal: Image Resurfacing to Aid Model's Robust Prediction

Detection Defenses: An Empty Promise against Adversarial Patch Attacks on Optical Flow

PatchCURE: Improving Certifiable Robustness, Model Utility, and Computation Efficiency of Adversarial Patch Defenses

Targeted Adversarial Attacks on Generalizable Neural Radiance Fields

SlowFormer: Universal Adversarial Patch for Attack on Compute and Energy Efficiency of Inference Efficient Vision Transformers

Defending Against Physical Adversarial Patch Attacks on Infrared Human Detection

AdvCLIP: Downstream-agnostic Adversarial Examples in Multimodal Contrastive Learning

Generating Transferable and Stealthy Adversarial Patch via Attention-guided Adversarial Inpainting

SAAM: Stealthy Adversarial Attack on Monocular Depth Estimation

Kidnapping Deep Learning-based Multirotors using Optimized Flying Adversarial Patches

Unified Adversarial Patch for Visible-Infrared Cross-modal Attacks in the Physical World

Defending Adversarial Patches via Joint Region Localizing and Inpainting

Diffusion to Confusion: Naturalistic Adversarial Patch Generation Based on Diffusion Model for Object Detector

Unified Adversarial Patch for Cross-modal Attacks in the Physical World

Random Position Adversarial Patch for Vision Transformers

Distributional Modeling for Location-Aware Adversarial Patches

Revisiting Image Classifier Training for Improved Certified Robust Defense against Adversarial Patches

Eigenpatches -- Adversarial Patches from Principal Components