# Adversarial Semantic Contour for Object Detection

arXiv: https://arxiv.org/abs/2109.15009 · HTML: https://mlsanity.com/paper/2109.15009/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 14 references that are in the map.
- First posted on arXiv 30 Sep 2021.

## Builds on (most cited first, 11 of 11)

- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [SSD: Single Shot MultiBox Detector](https://mlsanity.com/paper/1512.02325/) (2015)
- [YOLOv3: An Incremental Improvement](https://mlsanity.com/paper/1804.02767/) (2018)
- [YOLOv4: Optimal Speed and Accuracy of Object Detection](https://mlsanity.com/paper/2004.10934/) (2020)
- [YOLO9000: Better, Faster, Stronger](https://mlsanity.com/paper/1612.08242/) (2016)
- [MMDetection: Open MMLab Detection Toolbox and Benchmark](https://mlsanity.com/paper/1906.07155/) (2019)
- [Fooling automated surveillance cameras: adversarial patches to attack person detection](https://mlsanity.com/paper/1904.08653/) (2019)
- [Universal Physical Camouflage Attacks on Object Detectors](https://mlsanity.com/paper/1909.04326/) (2019)
- [DPAttack: Diffused Patch Attacks against Universal Object Detection](https://mlsanity.com/paper/2010.11679/) (2020)

## Built on by (most cited first, 6 of 6)

- [Understanding the Robustness of 3D Object Detection with Bird's-Eye-View Representations in Autonomous Driving](https://mlsanity.com/paper/2303.17297/) (2023)
- [Effectiveness Assessment of Recent Large Vision-Language Models](https://mlsanity.com/paper/2403.04306/) (2024)
- [Object Detectors in the Open Environment: Challenges, Solutions, and Outlook](https://mlsanity.com/paper/2403.16271/) (2024)
- [Environmental Matching Attack Against Unmanned Aerial Vehicles Object Detection](https://mlsanity.com/paper/2405.07595/) (2024)
- [SNEAK: Synonymous Sentences-Aware Adversarial Attack on Natural Language Video Localization](https://mlsanity.com/paper/2112.04154/) (2021)
- [Patch is Enough: Naturalistic Adversarial Patch against Vision-Language Pre-training Models](https://mlsanity.com/paper/2410.04884/) (2024)

## Abstract (arXiv)

Modern object detectors are vulnerable to adversarial examples, which brings potential risks to numerous applications, e.g., self-driving car. Among attacks regularized by ℓp norm, ℓ0-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 ℓ0 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.