paper-with-me

홈 › Papers

Adversarial YOLO: Defense Human Detection Patch Attacks via Detecting Adversarial Patches

2021-03-16 · Nan Ji, YanFei Feng, Haidong Xie, Xueshuang Xiang, Naijin Liu

The security of object detection systems has attracted increasing attention, especially when facing adversarial patch attacks. Since patch attacks change the pixels in a restricted area on objects, they are easy to implement in the physical world, especially for attacking human detection systems. The existing defenses against patch attacks are mostly applied for image classification problems and have difficulty resisting human detection attacks. Towards this critical issue, we propose an efficient and effective plug-in defense component on the YOLO detection system, which we name Ad-YOLO. The main idea is to add a patch class on the YOLO architecture, which has a negligible inference increment. Thus, Ad-YOLO is expected to directly detect both the objects of interest and adversarial patches. To the best of our knowledge, our approach is the first defense strategy against human detection attacks. We investigate Ad-YOLO's performance on the YOLOv2 baseline. To improve the ability of Ad-YOLO to detect variety patches, we first use an adversarial training process to develop a patch dataset based on the Inria dataset, which we name Inria-Patch. Then, we train Ad-YOLO by a combination of Pascal VOC, Inria, and Inria-Patch datasets. With a slight drop of $0.70\%$ mAP on VOC 2007 test set, Ad-YOLO achieves $80.31\%$ AP of persons, which highly outperforms $33.93\%$ AP for YOLOv2 when facing white-box patch attacks. Furthermore, compared with YOLOv2, the results facing a physical-world attack are also included to demonstrate Ad-YOLO's excellent generalization ability.

📄 PDF Abstract BibTeX arXiv:2103.08860

Code (0)

등록된 구현이 없습니다.

Tasks

Human Detectionimage-classificationImage Classificationobject-detectionObject Detection

Methods 이 논문이 사용한 방법론

YOLO 설명 없음
Average Pooling 설명 없음
1x1 Convolution A 1 x 1 Convolution is a convolution with some special properties in that it can be used for dimensionality reduction,…
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…
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…
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 $x$…
Batch Normalization 설명 없음
Max Pooling Max Pooling is a pooling operation that calculates the maximum value for patches of a feature map, and uses it to create a downsampled (pooled) feature map. It is usually…

Similar Papers 제목 키워드 기반

I Don't Know You, But I Can Catch You: Real-Time Defense against Diverse Adversarial Patches for Object Detectors

2024-06-12 · Zijin Lin, Yue Zhao, Kai Chen, Jinwen He

Deep neural networks (DNNs) have revolutionized the field of computer vision like object detection with their unparalleled performance. However, existing research has shown that DNNs are vulnerable to adversarial attacks…

object-detectionObject Detection

Defending Against Physical Adversarial Patch Attacks on Infrared Human Detection

2023-09-27 · Lukas Strack, Futa Waseda, Huy H. Nguyen, Yinqiang Zheng 외

Infrared detection is an emerging technique for safety-critical tasks owing to its remarkable anti-interference capability. However, recent studies have revealed that it is vulnerable to physically-realizable adversarial…

Data AugmentationHuman Detection

Breaking the Illusion: Real-world Challenges for Adversarial Patches in Object Detection

2024-10-23 · Jakob Shack, Katarina Petrovic, Olga Saukh

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 fo…

object-detectionObject Detection

TPatch: A Triggered Physical Adversarial Patch

2023-12-30 · Wenjun Zhu, Xiaoyu Ji, Yushi Cheng, Shibo Zhang 외

Autonomous vehicles increasingly utilize the vision-based perception module to acquire information about driving environments and detect obstacles. Correct detection and classification are important to ensure safe drivin…

Autonomous Vehicles

We Can Always Catch You: Detecting Adversarial Patched Objects WITH or WITHOUT Signature

2021-06-09 · Bin Liang, Jiachun Li, Jianjun Huang

Recently, the object detection based on deep learning has proven to be vulnerable to adversarial patch attacks. The attackers holding a specially crafted patch can hide themselves from the state-of-the-art person detecto…

object-detectionObject Detection