Backdoor Attacks on Deep Learning Face Detection
This addresses security risks in face recognition systems for applications in surveillance or authentication, but is incremental as it builds on existing backdoor attack concepts.
The paper introduced Face Generation Attacks and a Landmark Shift Attack to backdoor face detection systems, demonstrating vulnerabilities in bounding box and landmark coordinate regression, and proposed mitigations.
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.