RPATTACK: Refined Patch Attack on General Object Detectors

2021-03-23 · Hao Huang, Yongtao Wang, Zhaoyu Chen, Zhi Tang, Wenqiang Zhang, Kai-Kuang Ma

Nowadays, general object detectors like YOLO and Faster R-CNN as well as their variants are widely exploited in many applications. Many works have revealed that these detectors are extremely vulnerable to adversarial patch attacks. The perturbed regions generated by previous patch-based attack works on object detectors are very large which are not necessary for attacking and perceptible for human eyes. To generate much less but more efficient perturbation, we propose a novel patch-based method for attacking general object detectors. Firstly, we propose a patch selection and refining scheme to find the pixels which have the greatest importance for attack and remove the inconsequential perturbations gradually. Then, for a stable ensemble attack, we balance the gradients of detectors to avoid over-optimizing one of them during the training phase. Our RPAttack can achieve an amazing missed detection rate of 100% for both Yolo v4 and Faster R-CNN while only modifies 0.32% pixels on VOC 2007 test set. Our code is available at https://github.com/VDIGPKU/RPAttack.

📄 PDF Abstract BibTeX arXiv:2103.12469

Code (1)

VDIGPKU/RPAttack 공식 구현 pytorch

Tasks

Object

Methods 이 논문이 사용한 방법론

YOLO 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…

RoIPool 설명 없음

RPN A Region Proposal Network, or RPN, is a fully convolutional network that simultaneously predicts object bounds and objectness scores at each position. The RPN is trained…

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 $x$…

Faster R-CNN Faster R-CNN is an object detection model that improves on Fast R-CNN by utilising a region proposal network…

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

2021-12-08 · CVPR 2022 1 · Jiang Liu, Alexander Levine, Chun Pong Lau, Rama Chellappa 외

Object detection plays a key role in many security-critical systems. Adversarial patch attacks, which are easy to implement in the physical world, pose a serious threat to state-of-the-art object detectors. Developing re…

Adversarial Attack Detection Adversarial Defense Adversarial Robustness Object+3

Enhancing Remote Adversarial Patch Attacks on Face Detectors with Tiling and Scaling

2024-12-11 · Masora Okano, Koichi Ito, Masakatsu Nishigaki, Tetsushi Ohki

This paper discusses the attack feasibility of Remote Adversarial Patch (RAP) targeting face detectors. The RAP that targets face detectors is similar to the RAP that targets general object detectors, but the former has …

Deep Learning of Local RGB-D Patches for 3D Object Detection and 6D Pose Estimation

2016-07-20 · Wadim Kehl, Fausto Milletari, Federico Tombari, Slobodan Ilic 외

We present a 3D object detection method that uses regressed descriptors of locally-sampled RGB-D patches for 6D vote casting. For regression, we employ a convolutional auto-encoder that has been trained on a large collec…

3D Object Detection 6D Pose Estimation 6D Pose Estimation using RGB Object+4

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

2022-07-05 · Ke Xu, Yao Xiao, Zhaoheng Zheng, Kaijie Cai 외

Adversarial patch attacks mislead neural networks by injecting adversarial pixels within a local region. Patch attacks can be highly effective in a variety of tasks and physically realizable via attachment (e.g. a sticke…

Diversity image-classification Image Classification object-detection+3

Hidden Patch Attacks for Optical Flow

2021-06-18 · ICML Workshop AML 2021 7 · Benjamin Wortman

Adversarial patches have been of interest to researchers in recent years due to their easy implementation in real world attacks. In this paper we expand upon previous research by demonstrating a new "hidden" patch attack…

Object Recognition Optical Flow Estimation Semantic Segmentation