paper-with-me

홈 › Papers

Design and Interpretation of Universal Adversarial Patches in Face Detection

2019-11-30 · ECCV 2020 8 · Xiao Yang, Fangyun Wei, Hongyang Zhang, Jun Zhu

We consider universal adversarial patches for faces -- small visual elements whose addition to a face image reliably destroys the performance of face detectors. Unlike previous work that mostly focused on the algorithmic design of adversarial examples in terms of improving the success rate as an attacker, in this work we show an interpretation of such patches that can prevent the state-of-the-art face detectors from detecting the real faces. We investigate a phenomenon: patches designed to suppress real face detection appear face-like. This phenomenon holds generally across different initialization, locations, scales of patches, backbones, and state-of-the-art face detection frameworks. We propose new optimization-based approaches to automatic design of universal adversarial patches for varying goals of the attack, including scenarios in which true positives are suppressed without introducing false positives. Our proposed algorithms perform well on real-world datasets, deceiving state-of-the-art face detectors in terms of multiple precision/recall metrics and transferability.

📄 PDF Abstract BibTeX arXiv:1912.05021

Code (0)

등록된 구현이 없습니다.

Tasks

Face Detection

Similar Papers 제목 키워드 기반

Meta Adversarial Training against Universal Patches

2021-01-27 · Jan Hendrik Metzen, Nicole Finnie, Robin Hutmacher

Recently demonstrated physical-world adversarial attacks have exposed vulnerabilities in perception systems that pose severe risks for safety-critical applications such as autonomous driving. These attacks place adversar…

Autonomous Drivingimage-classificationImage ClassificationMeta-Learning

Adversarial Patch

2017-12-27 · Tom B. Brown, Dandelion Mané, Aurko Roy, Martín Abadi 외

We present a method to create universal, robust, targeted adversarial image patches in the real world. The patches are universal because they can be used to attack any scene, robust because they work under a wide variety…

Fooling Network Interpretation in Image Classification

2018-12-06 · ICCV 2019 10 · Akshayvarun Subramanya, Vipin Pillai, Hamed Pirsiavash

Deep neural networks have been shown to be fooled rather easily using adversarial attack algorithms. Practical methods such as adversarial patches have been shown to be extremely effective in causing misclassification. H…

Adversarial AttackClassificationDecision MakingGeneral Classification+3

Adversarial Manhole: Challenging Monocular Depth Estimation and Semantic Segmentation Models with Patch Attack

2024-08-27 · Naufal Suryanto, Andro Aprila Adiputra, Ahmada Yusril Kadiptya, Yongsu Kim 외

Monocular depth estimation (MDE) and semantic segmentation (SS) are crucial for the navigation and environmental interpretation of many autonomous driving systems. However, their vulnerability to practical adversarial at…

Adversarial AttackAutonomous DrivingDepth EstimationMonocular Depth Estimation+2

Defending Against Universal Adversarial Patches by Clipping Feature Norms

2021-01-01 · ICCV 2021 10 · Cheng Yu, Jiansheng Chen, Youze Xue, Yuyang Liu 외

Physical-world adversarial attacks based on universal adversarial patches have been proved to be able to mislead deep convolutional neural networks (CNNs), exposing the vulnerability of real-world visual classificati…