AdaForensics: Learning A Characteristic-aware Adaptive Deepfake Detector
2026-08-03 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors propose AdaForensics, a new method for detecting deepfake images that adapts to different facial characteristics rather than using one fixed detector for all faces. Their system learns general features applicable to any face, as well as features specific to individual faces, and adjusts its detection approach accordingly using a special two-part network called a HyperNetwork. This approach allows the detector to better handle variations between faces when spotting deepfakes. Tests on popular deepfake datasets show that AdaForensics works better than previous methods.
Deepfake detectionAdaptive networkHyperNetworkFacial characteristicsCharacteristic-aware embeddingsTwo-branch networkFaceForensics datasetCeleb-DF datasetDFDC datasetForgery detection
Authors
Xiaoke Yang, Haixu Song, Xiangyu Lu, Shao-Lun Huang, Yueqi Duan
Abstract
In this paper, we propose a characteristic-aware adaptive network named AdaForensics for deepfake detection. Most existing methods learn a fixed network to detect deepfakes based on carefully-designed network architectures. However, these methods employ the same deepfake detector for all the images despite of various facial characteristic, which fail to provide customized forgery detection for different individuals. To address this, our AdaForensics simultaneously learns characteristic-agnostic and characteristic-specific embeddings, where the detector dynamically adapts to varying faces with our designed hypernetwork on the fly. More specifically, our AdaForensics not only explores the shareable abstractions from various deepfake images, but also adapts the detector to the given characteristic at test time. To achieve this, we propose a two-branch HyperNetwork to learn an adaptive deepfake detector, which automatically adjusts the parameters based on characteristic of the input. Extensive experiments on widely-used datasets including FaceForensics, Celeb-DF and DFDC demonstrate our AdaForensics outperforms the state-of-the-art works.