IPatch: A Remote Adversarial Patch

2021-04-30 · Yisroel Mirsky

Applications such as autonomous vehicles and medical screening use deep learning models to localize and identify hundreds of objects in a single frame. In the past, it has been shown how an attacker can fool these models by placing an adversarial patch within a scene. However, these patches must be placed in the target location and do not explicitly alter the semantics elsewhere in the image. In this paper, we introduce a new type of adversarial patch which alters a model's perception of an image's semantics. These patches can be placed anywhere within an image to change the classification or semantics of locations far from the patch. We call this new class of adversarial examples `remote adversarial patches' (RAP). We implement our own RAP called IPatch and perform an in-depth analysis on image segmentation RAP attacks using five state-of-the-art architectures with eight different encoders on the CamVid street view dataset. Moreover, we demonstrate that the attack can be extended to object recognition models with preliminary results on the popular YOLOv3 model. We found that the patch can change the classification of a remote target region with a success rate of up to 93% on average.

📄 PDF Abstract BibTeX arXiv:2105.00113

Code (0)

등록된 구현이 없습니다.

Tasks

Autonomous Vehicles Image Segmentation Object Recognition Semantic Segmentation

Methods 이 논문이 사용한 방법론

Average Pooling 설명 없음

Global Average Pooling Global Average Pooling is a pooling operation designed to replace fully connected layers in classical CNNs. The idea is to generate one feature map for each corresponding…

Residual Connection 설명 없음

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

k-Means Clustering k-Means Clustering is a clustering algorithm that divides a training set into $k$ different clusters of examples that are near each other. It works by initializing $k$…

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

1x1 Convolution A 1 x 1 Convolution is a convolution with some special properties in that it can be used for dimensionality reduction,…

Logistic Regression Logistic Regression, despite its name, is a linear model for classification rather than regression. Logistic regression is also known in the literature as logit regression,…

OmniPatch: A Universal Adversarial Patch for ViT-CNN Cross-Architecture Transfer in Semantic Segmentation

2026-03-21 · Aarush Aggarwal, Akshat Tomar, Amritanshu Tiwari, Sargam Goyal arxiv

Robust semantic segmentation is crucial for safe autonomous driving, yet deployed models remain vulnerable to black-box adversarial attacks when target weights are unknown. Most existing approaches either craft image-wid…

Semantic Segmentation Autonomous Driving

Hiding in Plain Sight: An Effective Physical Adversarial Patch Attack against Visual-Infrared Fused Face Detection

2026-07-25 · Qiucheng Yu, Tao Ni, Yihe Zhou, Jiayimei Wang 외 arxiv

Deep learning-based visual-infrared fused face detection models are increasingly deployed across a wide range of applications, yet they remain susceptible to adversarial patch attacks. Most prior attacks target either th…

Face Detection

Transferable Physical-World Adversarial Patches Against Pedestrian Detection Models

2026-04-24 · Shihui Yan, Ziqi Zhou, Yufei Song, Yifan Hu 외 arxiv

Physical adversarial patch attacks critically threaten pedestrian detection, causing surveillance and autonomous driving systems to miss pedestrians and creating severe safety risks. Despite their effectiveness in contro…

Pedestrian Detection Autonomous Driving Data Augmentation

IPatch: A Multi-Resolution Transformer Architecture for Robust Time-Series Forecasting

2026-03-25 · Aymane Harkati, Moncef Garouani, Olivier Teste, Julien Aligon 외 arxiv

Accurate forecasting of multivariate time series remains challenging due to the need to capture both short-term fluctuations and long-range temporal dependencies. Transformer-based models have emerged as a powerful appro…

Replay-free Online Continual Learning with Self-Supervised MultiPatches

2025-02-13 · Giacomo Cignoni, Andrea Cossu, Alex Gomez-Villa, Joost Van de Weijer 외

Online Continual Learning (OCL) methods train a model on a non-stationary data stream where only a few examples are available at a time, often leveraging replay strategies. However, usage of replay is sometimes forbidden…

Continual Learning Self-Supervised Learning