Adversarial Semantic Contour for Object Detection
Modern object detectors are vulnerable to adversarial examples, which brings potential risks to numerous applications, e.g., self-driving car. Among attacks regularized by $\ell_p$ norm, $\ell_0$-attack aims to modify as few pixels as possible. Nevertheless, the problem is nontrivial since it generally requires to optimize the shape along with the texture simultaneously, which is an NP-hard problem. To address this issue, we propose a novel method of Adversarial Semantic Contour (ASC) guided by object contour as prior. With this prior, we reduce the searching space to accelerate the $\ell_0$ optimization, and also introduce more semantic information which should affect the detectors more. Based on the contour, we optimize the selection of modified pixels via sampling and their colors with gradient descent alternately. Extensive experiments demonstrate that our proposed ASC outperforms the most commonly manually designed patterns (e.g., square patches and grids) on task of disappearing. By modifying no more than 5\% and 3.5\% of the object area respectively, our proposed ASC can successfully mislead the mainstream object detectors including the SSD512, Yolov4, Mask RCNN, Faster RCNN, etc.
Code (0)
등록된 구현이 없습니다.
Tasks
Objectobject-detectionObject DetectionSimilar Papers 제목 키워드 기반
To Make Yourself Invisible with Adversarial Semantic Contours
Modern object detectors are vulnerable to adversarial examples, which may bring risks to real-world applications. The sparse attack is an important task which, compared with the popular adversarial perturbation on the wh…
Autonomous DrivingObjectobject-detectionObject DetectionConvolutional Oriented Boundaries: From Image Segmentation to High-Level Tasks
We present Convolutional Oriented Boundaries (COB), which produces multiscale oriented contours and region hierarchies starting from generic image classification Convolutional Neural Networks (CNNs). COB is computational…
Boundary DetectionContour Detectionimage-classificationImage Classification+6Joint Object Contour Points and Semantics for Instance Segmentation
The attributes of object contours has great significance for instance segmentation task. However, most of the current popular deep neural networks do not pay much attention to the object edge information. Inspired by the…
Instance SegmentationKeypoint DetectionMulti-Task LearningObject+2FineFool: Fine Object Contour Attack via Attention
Machine learning models have been shown vulnerable to adversarial attacks launched by adversarial examples which are carefully crafted by attacker to defeat classifiers. Deep learning models cannot escape the attack eith…
Adversarial AttackObjectRecurrent Generic Contour-based Instance Segmentation with Progressive Learning
Contour-based instance segmentation has been actively studied, thanks to its flexibility and elegance in processing visual objects within complex backgrounds. In this work, we propose a novel deep network architecture, i…
Instance SegmentationLane DetectionObjectScene Text Detection+4