数据与计算发展前沿2023，Vol.5Issue(6)：42-57,16.DOI:10.11871/jfdc.issn.2096-742X.2023.06.005
基于增量学习的深度人脸伪造检测
Deepfake Detection Based on Incremental Learning
摘要
Abstract
[Objective]With the development of computer vision,computer graphics and deep learning technologies,deep face forgery(DeepFake)technology has achieved realistic effects.If used il-legally,it will bring serious security risks to individuals,society and the country.Most existing face forgery detec-tion methods infer or predict a specific"fingerprint"of forged faces through one-time training for authenticity de-tection.When facing new types of forgery,these methods use all data to retrain the network to maintain their de-tection ability,otherwise their detection effect will drop sharply.However,retraining the network requires a rela-tively high cost and hinders the model's ability to learn new knowledge in real-time.In view of this,this paper proposes an incremental learning method for detecting forged faces.[Method]The method introduces a dynamic and scalable incremental learning framework to ensure that the model can retain memory of old knowledge while absorbing new knowledge,uses multi-classification to guide binary classification to improve the model's classifi-cation ability,and ultimately achieves accurate classification of face images.[Result]Experiments are conducted on two public datasets.On the FF++ expansion set and the ForgeryNet expansion set defined in the experiment,our method can simultaneously maintain the performance of face forgery detection on both old and new tasks.On the ForgeryNet expansion set,existing face forgery detection methods achieves an average accuracy of nearly 98.33%,while our method achieves an average accuracy of 96.16%,while the former uses three times more stor-age and computing resources than the latter.The last five tasks of the expansion set of ForgeryNet in the experi-ment are considered as new tasks,with each class containing only 100 training data.Existing methods achieves an average accuracy of near 88.72%on these five tasks,while the method proposed in this paper achieves an aver-age accuracy of 93.83%.[Limitations]To maintain a balance of positive and negative samples,pairs of training samples are required for training,which introduces unnecessary training data and increases the training burden.[Conclusion]The face forgery detection method proposed in this paper improves the effectiveness of the model in detecting constantly emerging forgery samples through incremental learning.Experimental results show that this method can achieve detection capability comparable to existing methods at a lower computational cost;and achieve better forgery detection capability than existing methods in the case of limited training data.关键词
深度人脸伪造检测/深度伪造/增量学习/连续学习/灾难性遗忘Key words
deepfake detection/deep fakes/incremental learning/continuous learning/catastrophic forgetting引用本文复制引用
赵泽军,范振峰,丁博,夏时洪..基于增量学习的深度人脸伪造检测[J].数据与计算发展前沿,2023,5(6):42-57,16.基金项目
国家自然科学基金项目(62106250)和博士后面上基金项目(2021M703272) （62106250）
