TY - GEN
T1 - Aggregating Layers for Deepfake Detection
AU - Jevnisek, Amir
AU - Avidan, Shai
N1 - Publisher Copyright:
© 2022 IEEE.
PY - 2022
Y1 - 2022
N2 - The increasing popularity of facial manipulation (Deepfakes) and synthetic face creation raises the need to develop robust forgery detection solutions. Crucially, most work in this domain assume that the Deepfakes in the test set come from the same Deepfake algorithms that were used for training the network. This is not how things work in practice. Instead, we consider the case where the network is trained on one Deepfake algorithm, and tested on Deepfakes generated by another algorithm. Typically, supervised techniques follow a pipeline of visual feature extraction from a deep backbone, followed by a binary classification head. Instead, our algorithm aggregates features extracted across all layers of one backbone network to detect a fake. We evaluate our approach on two domains of interest Deepfake detection and Synthetic image detection, and find that we achieve SOTA results.
AB - The increasing popularity of facial manipulation (Deepfakes) and synthetic face creation raises the need to develop robust forgery detection solutions. Crucially, most work in this domain assume that the Deepfakes in the test set come from the same Deepfake algorithms that were used for training the network. This is not how things work in practice. Instead, we consider the case where the network is trained on one Deepfake algorithm, and tested on Deepfakes generated by another algorithm. Typically, supervised techniques follow a pipeline of visual feature extraction from a deep backbone, followed by a binary classification head. Instead, our algorithm aggregates features extracted across all layers of one backbone network to detect a fake. We evaluate our approach on two domains of interest Deepfake detection and Synthetic image detection, and find that we achieve SOTA results.
UR - http://www.scopus.com/inward/record.url?scp=85143618111&partnerID=8YFLogxK
U2 - 10.1109/ICPR56361.2022.9956052
DO - 10.1109/ICPR56361.2022.9956052
M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.conference???
AN - SCOPUS:85143618111
T3 - Proceedings - International Conference on Pattern Recognition
SP - 2027
EP - 2033
BT - 2022 26th International Conference on Pattern Recognition, ICPR 2022
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 26th International Conference on Pattern Recognition, ICPR 2022
Y2 - 21 August 2022 through 25 August 2022
ER -