Design and Interpretation of Universal Adversarial Patches in Face Detection
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Face DetectionSimilar Papers 제목 키워드 기반
Meta Adversarial Training against Universal Patches
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-LearningAdversarial Patch
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
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+3Adversarial Manhole: Challenging Monocular Depth Estimation and Semantic Segmentation Models with Patch Attack
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+2Defending Against Universal Adversarial Patches by Clipping Feature Norms
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…