Backdoor Attacks on Deep Learning Face Detection
Preprint
Abstract
Face Recognition Systems that operate in unconstrained environments capture images under varying conditions,such as inconsistent lighting, or diverse face poses. These challenges require including a Face Detection module that regresses bounding boxes and landmark coordinates for proper Face Alignment. This paper shows the effectiveness of Object Generation Attacks on Face Detection, dubbed Face Generation Attacks, and demonstrates for the first time a Landmark Shift Attack that backdoors the coordinate regression task performed by face detectors. We then offer mitigations against these vulnerabilities.Keywords
All Related Versions
This publication has 15 references indexed in Scilit:
- Machine learning-based real-time anomaly detection using data pre-processing in the telemetry of server farmsScientific Reports, 2024
- A Comprehensive Survey on Backdoor Attacks and Their Defenses in Face Recognition SystemsIEEE Access, 2024
- BadDet: Backdoor Attacks on Object Detection2023
- Research on anomaly detection method of nuclear power plant operation state based on unsupervised deep generative modelAnnals of Nuclear Energy, 2022
- MobileNetV2: Inverted Residuals and Linear Bottlenecks2018
- Focal Loss for Dense Object Detection2017
- Deep Residual Learning for Image Recognition2016
- You Only Look Once: Unified, Real-Time Object Detection2016
- Microsoft COCO: Common Objects in Context2014
- The Pascal Visual Object Classes (VOC) ChallengeInternational Journal of Computer Vision, 2009