Hiding Faces in Plain Sight: Defending DeepFakes by Disrupting Face Detection

TL;DR

This paper proposes FacePoison, an adversarial attack framework that sabotages face detection in videos to prevent DeepFake creation, validated across multiple detectors and DeepFake models.

Contribution

Introduction of FacePoison, a proactive defense disrupting face detection to hinder DeepFake synthesis, including an efficient VideoFacePoison strategy for videos.

Findings

FacePoison effectively disrupts face detectors across five models.

VideoFacePoison reduces computational cost while maintaining attack performance.

Disruption of face detection hampers DeepFake generation across eleven models.

Abstract

This paper investigates the feasibility of a proactive DeepFake defense framework, {\em FacePosion}, to prevent individuals from becoming victims of DeepFake videos by sabotaging face detection. The motivation stems from the reliance of most DeepFake methods on face detectors to automatically extract victim faces from videos for training or synthesis (testing). Once the face detectors malfunction, the extracted faces will be distorted or incorrect, subsequently disrupting the training or synthesis of the DeepFake model. To achieve this, we adapt various adversarial attacks with a dedicated design for this purpose and thoroughly analyze their feasibility. Based on FacePoison, we introduce {\em VideoFacePoison}, a strategy that propagates FacePoison across video frames rather than applying them individually to each frame. This strategy can largely reduce the computational overhead while retaining the favorable attack performance. Our method is validated on five face detectors, and extensive experiments against eleven different DeepFake models demonstrate the effectiveness of disrupting face detectors to hinder DeepFake generation.