雖然現有的人臉反欺騙(FAS)或深度造假(Deepfake)檢測方法在性能方面是有效的，但它們通常使用大量的參數，因此十分耗費硬體資源，不適合手持設備。除此之外，他們花了很多時間訓練因為他們以普通監督式學習(Supervised-Learning)來處理假臉辨識議題上的各種造假形式，但這往往需要大量的訓練資料以及時間來應付更多元的攻擊型態與不同的人像環境。綜上所述，為了克服人臉反欺騙或深度造假領域的挑戰，學習從預定義的演示攻擊中歸納出欺騙類型的鑑別特徵，同時賦予模型學習的能力，使模型不僅能學習一種造假特徵，還能快速適應其他類似的造假特徵也是一個重要的問題。我們提出了一種基於批量樣本間關係的嵌入空間特徵損失策略，通過自訂一的損失函數鼓勵明確區分假臉和真臉樣本，使得類別間的邊界更為清晰來促使分類更加準確。同時，我們還將這種基於度量學習(Metric Learning)方法與一種基於少樣本學習(Few-shot Learning)的方法結合，更好地發揮兩種方法的優勢。並通過比較參數的數量、FLOPS和其他先進的方法的基線，進一步展示了我們的模型的可靠性。

Although the existing face anti-spoofing(FAS) or Deepfake detection approaches are effective in terms of performance, they usually use a significant amount of parameters that make them resource-heavy and unsuitable for handheld devices. Apart from this, they spend a lot of time to training since they have defined face deception as a supervised learning problem to detect various predefined presentation attacks, which requires a large amount of training data to cover as many attacks as possible, and requires a lot of time to adapt to a new environment. In summary, to overcome the challenge in the field of face anti-spoofing or DeepFake, learn discriminative features that can generalize to unseen spoofing types from predefined presentation attacks. Meanwhile, endowing computer programs with the ability to learn and make a computer not only learns a behavior but also how to adapt its behavior is also an important issue. In this thesis, we propose a new embedding loss strategy that operates on the relationships between samples in a batch, while classification losses include a weight matrix that transforms the embedding space into a vector of class logits. Encourages differentiation between spoof and live samples by making clear boundaries between them. With clear boundaries, classification becomes more accurate. At the same time, we also combine this metric learning-based method with a few-shot learning-based method to better play the advantages of the two methods. In addition, we further demonstrate our model's capabilities by comparing the number of parameters, FLOPS, and performance with other state-of-the-art methods.

[1] BBC Bitesize, “Deepfakes: What Are They and Why Would I Make One?”2019. [Online]. Avail- able: https://www.bbc.co.uk/bitesize/articles/zfkwcqt
[2] Boulkenafet, Z., Komulainen, J., & Hadid, A. (2015, September). Face anti-spoofing based on color texture analysis. In 2015 IEEE international conference on image processing (ICIP) (pp. 2636-2640). IEEE.
[3] de Freitas Pereira, T., Anjos, A., De Martino, J. M., & Marcel, S. (2012, November). LBP− TOP based countermeasure against face spoofing attacks. In Asian Conference on Computer Vision (pp. 121-132). Springer, Berlin, Heidelberg.
[4] Komulainen, J., Hadid, A., & Pietikäinen, M. (2013, September). Context based face anti-spoofing. In 2013 IEEE Sixth International Conference on Biometrics: Theory, Applications and Systems (BTAS) (pp. 1-8). IEEE.
[5] Yang, J., Lei, Z., Liao, S., & Li, S. Z. (2013, June). Face liveness detection with component dependent descriptor. In 2013 International Conference on Biometrics (ICB) (pp. 1-6). IEEE.
[6] Patel, K., Han, H., & Jain, A. K. (2016). Secure face unlock: Spoof detection on smartphones. IEEE transactions on information forensics and security, 11(10), 2268-2283.
[7] Chang, C. C., & Lin, C. J. (2011). LIBSVM: a library for support vector machines. ACM transactions on intelligent systems and technology (TIST), 2(3), 1-27.
[8] Liu, Y., Jourabloo, A., & Liu, X. (2018). Learning deep models for face anti-spoofing: Binary or aux- iliary supervision. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 389-398).
[9] Qin, Y., Zhao, C., Zhu, X., Wang, Z., Yu, Z., Fu, T., ... & Lei, Z. (2020, April). Learning meta model for zero-and few-shot face anti-spoofing. In Proceedings of the AAAI Conference on Artificial Intel- ligence (Vol. 34, No. 07, pp. 11916-11923).
[10] Boulkenafet, Z., Komulainen, J., & Hadid, A. (2015, September). Face anti-spoofing based on color texture analysis. In 2015 IEEE international conference on image processing (ICIP) (pp. 2636-2640). IEEE.
[11] Komulainen, J., Hadid, A., & Pietikäinen, M. (2013, September). Context-based face anti-spoofing. In 2013 IEEE Sixth International Conference on Biometrics: Theory, Applications and Systems (BTAS) (pp. 1-8). IEEE.
[12] de Freitas Pereira, T., Anjos, A., De Martino, J. M., & Marcel, S. (2012, November). LBP− TOP-based countermeasure against face spoofing attacks. In Asian Conference on Computer Vision (pp. 121-132). Springer, Berlin, Heidelberg.
[13] Yang, J., Lei, Z., Liao, S., & Li, S. Z. (2013, June). Face liveness detection with component dependent descriptor. In 2013 International Conference on Biometrics (ICB) (pp. 1-6). IEEE.
[14] Patel, K., Han, H., & Jain, A. K. (2016). Secure face unlock: Spoof detection on smartphones. IEEE transactions on information forensics and security, 11(10), 2268-2283.
[15] Boulkenafet, Z., Komulainen, J., & Hadid, A. (2016). Face antispoofing using speeded-up robust features and fisher vector encoding. IEEE Signal Processing Letters, 24(2), 141-145.
[16] Boulkenafet, Z., Komulainen, J., & Hadid, A. (2016). Face spoofing detection using colour texture analysis. IEEE Transactions on Information Forensics and Security, 11(8), 1818-1830.
[17] Peixoto, B., Michelassi, C., & Rocha, A. (2011, September). Face liveness detection under bad illumination conditions. In 2011 18th IEEE International Conference on Image Processing (pp. 3557-3560). IEEE.
[18] Feng, L., Po, L. M., Li, Y., Xu, X., Yuan, F., Cheung, T. C. H., & Cheung, K. W. (2016). Integration of image quality and motion cues for face anti-spoofing: A neural network approach. Journal of Visual Communication and Image Representation, 38, 451-460.
[19] Li, L., Feng, X., Boulkenafet, Z., Xia, Z., Li, M., & Hadid, A. (2016, December). An original face anti-spoofing approach using partial convolutional neural network. In 2016 Sixth International Conference on Image Processing Theory, Tools and Applications (IPTA) (pp. 1-6). IEEE.
[20] Patel, K., Han, H., & Jain, A. K. (2016, October). Cross-database face antispoofing with robust feature representation. In Chinese Conference on Biometric Recognition (pp. 611-619). Springer, Cham.
[21] Atoum, Y., Liu, Y., Jourabloo, A., & Liu, X. (2017, October). Face anti-spoofing using patch and depth-based CNNs. In 2017 IEEE International Joint Conference on Biometrics (IJCB) (pp. 319-328). IEEE.
[22] Kim, T., Kim, Y., Kim, I., & Kim, D. (2019). Basn: Enriching feature representation using bipartite auxiliary supervisions for face anti-spoofing. In Proceedings of the IEEE/CVF International Confer- ence on Computer Vision Workshops (pp. 0-0).
[23] Shao, R., Lan, X., & Yuen, P. C. (2020, April). Regularized fine-grained meta face anti-spoofing. In Proceedings of the AAAI Conference on Artificial Intelligence (Vol. 34, No. 07, pp. 11974-11981).
[24] Chang, C. C., & Lin, C. J. (2011). LIBSVM: a library for support vector machines. ACM transactions on intelligent systems and technology (TIST), 2(3), 1-27.
[25] Bromley, J., Bentz, J. W., Bottou, L., Guyon, I., LeCun, Y., Moore, C., ... & Shah, R. (1993). Signature verification using a “siamese”time delay neural network. International Journal of Pattern Recognition and Artificial Intelligence, 7(04), 669-688.
[26] Vinyals, O., Blundell, C., Lillicrap, T., & Wierstra, D. (2016). Matching networks for one-shot learning. Advances in neural information processing systems, 29, 3630-3638.
[27] Sung, F., Yang, Y., Zhang, L., Xiang, T., Torr, P. H., & Hospedales, T. M. (2018). Learning to compare: Relation network for few-shot learning. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 1199-1208).
[28] Snell, J., Swersky, K., & Zemel, R. S. (2017). Prototypical networks for few-shot learning. arXiv preprint arXiv:1703.05175.
[29] Finn, C., Abbeel, P., & Levine, S. (2017, July). Model-agnostic meta-learning for fast adaptation of deep networks. In International Conference on Machine Learning (pp. 1126-1135). PMLR.
[30] Nichol, A., Achiam, J., & Schulman, J. (2018). On first-order meta-learning algorithms. arXiv preprint arXiv:1803.02999.
[31] Shao, R., Lan, X., & Yuen, P. C. (2020, April). Regularized fine-grained meta face anti-spoofing. In Proceedings of the AAAI Conference on Artificial Intelligence (Vol. 34, No. 07, pp. 11974-11981).
[32] Qin, Y., Zhao, C., Zhu, X., Wang, Z., Yu, Z., Fu, T., ... & Lei, Z. (2020, April). Learning meta model for zero-and few-shot face anti-spoofing. In Proceedings of the AAAI Conference on Artificial Intel- ligence (Vol. 34, No. 07, pp. 11916-11923).
[33] Santoro, A., Bartunov, S., Botvinick, M., Wierstra, D., & Lillicrap, T. (2016, June). Meta-learning with memory-augmented neural networks. In International conference on machine learning (pp. 1842- 1850). PMLR.
[34] Munkhdalai, T., & Yu, H. (2017, July). Meta networks. In International Conference on Machine Learning (pp. 2554-2563). PMLR.
[35] Raghu, A., Raghu, M., Bengio, S., & Vinyals, O. (2019). Rapid learning or feature reuse? towards understanding the effectiveness of maml. arXiv preprint arXiv:1909.09157.
[36] Simo-Serra, E., Trulls, E., Ferraz, L., Kokkinos, I., Fua, P., & Moreno-Noguer, F. (2015). Discriminative learning of deep convolutional feature point descriptors. In Proceedings of the IEEE international conference on computer vision (pp. 118-126).
[37] Radosavovic, I., Kosaraju, R. P., Girshick, R., He, K., & Dollár, P. (2020). Designing network design spaces. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 10428-10436).
[38] Deng, J., Guo, J., Zhou, Y., Yu, J., Kotsia, I., & Zafeiriou, S. (2019). Retinaface: Single-stage dense face localisation in the wild. arXiv preprint arXiv:1905.00641.
[39] Loshchilov, I., & Hutter, F. (2017). Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101.
[40] Schroff, F., Kalenichenko, D., & Philbin, J. (2015). Facenet: A unified embedding for face recognition and clustering. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 815-823).
[41] Sun, Y., Cheng, C., Zhang, Y., Zhang, C., Zheng, L., Wang, Z., & Wei, Y. (2020). Circle loss: A unified perspective of pair similarity optimization. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 6398-6407).
[42] Xuan, H., Stylianou, A., & Pless, R. (2020). Improved embeddings with easy positive triplet mining. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (pp. 2474- 2482).
[43] Sun, Y., Wang, X., & Tang, X. (2014). Deep learning face representation from predicting 10,000 classes. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 1891- 1898).
[44] Liu, W., Wen, Y., Yu, Z., & Yang, M. (2016, June). Large-margin softmax loss for convolutional neural networks. In ICML (Vol. 2, No. 3, p. 7).
[45] Wen, Y., Zhang, K., Li, Z., & Qiao, Y. (2016, October). A discriminative feature learning approach for deep face recognition. In European conference on computer vision (pp. 499-515). Springer, Cham.
[46] Wang, F., Cheng, J., Liu, W., & Liu, H. (2018). Additive margin softmax for face verification. IEEE Signal Processing Letters, 25(7), 926-930.
[47] Wang, H., Wang, Y., Zhou, Z., Ji, X., Gong, D., Zhou, J., ... & Liu, W. (2018). Cosface: Large margin cosine loss for deep face recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 5265-5274).
[48] Deng, J., Guo, J., Xue, N., & Zafeiriou, S. (2019). Arcface: Additive angular margin loss for deep face recognition. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 4690-4699).
[49] Lin, J. D., Lin, H. H., Dy, J., Chen, J. C., Tanveer, M., Razzak, I., & Hua, K. L. (2021). Lightweight Face Anti-Spoofing Network for Telehealth Applications. IEEE Journal of Biomedical and Health Informatics.
[50] Zhang, Y., Yin, Z., Li, Y., Yin, G., Yan, J., Shao, J., & Liu, Z. (2020, August). Celeba-spoof: Large-scale face anti-spoofing dataset with rich annotations. In European Conference on Computer Vision (pp. 70-85). Springer, Cham.
[51] Selvaraju, R. R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., & Batra, D. (2017). Grad-cam: Visual explanations from deep networks via gradient-based localization. In Proceedings of the IEEE international conference on computer vision (pp. 618-626).
[52] Fu, R., Hu, Q., Dong, X., Guo, Y., Gao, Y., & Li, B. (2020). Axiom-based grad-cam: Towards accurate visualization and explanation of cnns. arXiv preprint arXiv:2008.02312.
[53] Khosla, P., Teterwak, P., Wang, C., Sarna, A., Tian, Y., Isola, P., ... & Krishnan, D. (2020). Supervised contrastive learning. arXiv preprint arXiv:2004.11362.
[54] Rossler, A., Cozzolino, D., Verdoliva, L., Riess, C., Thies, J., & Nießner, M. (2019). Faceforensics+
+: Learning to detect manipulated facial images. In Proceedings of the IEEE/CVF International Conference on Computer Vision (pp. 1-11).
[55] “Deepfakes github,”https://github.com/deepfakes/faceswap.
[56] Thies, J., Zollhöfer, M., & Nießner, M. (2019). Deferred neural rendering: Image synthesis using neural textures. ACM Transactions on Graphics (TOG), 38(4), 1-12.
[57] Zhang, J., Zeng, X., Pan, Y., Liu, Y., Ding, Y., & Fan, C. (2019). Faceswapnet: Landmark guided many-to-many face reenactment. arXiv preprint arXiv:1905.11805, 2.
[58] Thies, J., Zollhofer, M., Stamminger, M., Theobalt, C., & Nießner, M. (2016). Face2face: Real-time face capture and reenactment of rgb videos. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 2387-2395).
[59] Wang, S. Y., Wang, O., Zhang, R., Owens, A., & Efros, A. A. (2020). CNN-generated images are surprisingly easy to spot... for now. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 8695-8704).
[60] Chai, L., Bau, D., Lim, S. N., & Isola, P. (2020, August). What makes fake images detectable? un- derstanding properties that generalize. In European Conference on Computer Vision (pp. 103-120). Springer, Cham.
[61] Masi, I., Killekar, A., Mascarenhas, R. M., Gurudatt, S. P., & AbdAlmageed, W. (2020, August). Two- branch recurrent network for isolating deepfakes in videos. In European Conference on Computer Vision (pp. 667-684). Springer, Cham.
[62] Li, L., Bao, J., Zhang, T., Yang, H., Chen, D., Wen, F., & Guo, B. (2020). Face x-ray for more general face forgery detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 5001-5010).
[63] Sabir, E., Cheng, J., Jaiswal, A., AbdAlmageed, W., Masi, I., & Natarajan, P. (2019). Recurrent convolutional strategies for face manipulation detection in videos. Interfaces (GUI), 3(1), 80-87.
[64] Haliassos, A., Vougioukas, K., Petridis, S., & Pantic, M. (2021). Lips Don’t Lie: A Generalisable and Robust Approach To Face Forgery Detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 5039-5049).
[65] Hermans, A., Beyer, L., & Leibe, B. (2017). In defense of the triplet loss for person re-identification. arXiv preprint arXiv:1703.07737.