Optimizing Deep CNN Architectures for Face Liveness Detection

The quality and efficiency of generating face-swap images have been markedly strengthened by deep learning. For instance, the face-swap manipulations by DeepFake are so real that it is tricky to distinguish authenticity through automatic or manual detection. To augment the efficiency of distinguishing face-swap images generated by DeepFake from real facial ones, a novel counterfeit feature extraction technique was developed based on deep learning and error level analysis (ELA). It is related to entropy and information theory such as cross-entropy loss function in the final softmax layer. The DeepFake algorithm is only able to generate limited resolutions. Therefore, this algorithm results in two different image compression ratios between the fake face area as the foreground and the original area as the background, which would leave distinctive counterfeit traces. Through the ELA method, we can detect whether there are different image compression ratios. Convolution neural network (CNN), one of the representative technologies of deep learning, can extract the counterfeit feature and detect whether images are fake. Experiments show that the training efficiency of the CNN model can be significantly improved by the ELA method. In addition, the proposed technique can accurately extract the counterfeit feature, and therefore achieves outperformance in simplicity and efficiency compared with direct detection methods. Specifically, without loss of accuracy, the amount of computation can be significantly reduced (where the required floating-point computing power is reduced by more than 90%).

Section: Comparison With Other Methodsmentioning

confidence: 99%

A Novel Counterfeit Feature Extraction Technique for Exposing Face-Swap Images Based on Deep Learning and Error Level Analysis

Zhang

Zhao

2020

“…The Inception network’s architecture improves the utilization of computing resources within the network by increasing the depth and width of the network while keeping the computing budget constant. Filters of different sizes are employed in the same layer to handle the feature information of multiple scales, and then the features are aggregated in the next layer so that the fusion features of multiple scales can be extracted in the next Inception module [ 30 ]. The basic inception structure uses filters of sizes 1 × 1, 3 × 3, and 5 × 5, as shown in Figure 3 .…”

Section: Proposed Methodsmentioning

confidence: 99%

A Multi-Scale Feature Fusion Method Based on U-Net for Retinal Vessel Segmentation

Yang

Liu

Ren

et al. 2020

Computer-aided automatic segmentation of retinal blood vessels plays an important role in the diagnosis of diseases such as diabetes, glaucoma, and macular degeneration. In this paper, we propose a multi-scale feature fusion retinal vessel segmentation model based on U-Net, named MSFFU-Net. The model introduces the inception structure into the multi-scale feature extraction encoder part, and the max-pooling index is applied during the upsampling process in the feature fusion decoder of an improved network. The skip layer connection is used to transfer each set of feature maps generated on the encoder path to the corresponding feature maps on the decoder path. Moreover, a cost-sensitive loss function based on the Dice coefficient and cross-entropy is designed. Four transformations—rotating, mirroring, shifting and cropping—are used as data augmentation strategies, and the CLAHE algorithm is applied to image preprocessing. The proposed framework is tested and trained on DRIVE and STARE, and sensitivity (Sen), specificity (Spe), accuracy (Acc), and area under curve (AUC) are adopted as the evaluation metrics. Detailed comparisons with U-Net model, at last, it verifies the effectiveness and robustness of the proposed model. The Sen of 0.7762 and 0.7721, Spe of 0.9835 and 0.9885, Acc of 0.9694 and 0.9537 and AUC value of 0.9790 and 0.9680 were achieved on DRIVE and STARE databases, respectively. Results are also compared to other state-of-the-art methods, demonstrating that the performance of the proposed method is superior to that of other methods and showing its competitive results.

“…Various approaches have been proposed for face liveness detection on static images, such as analysis of texture differences between live and fake faces as in Reference [ 1 ], motion analysis, and deep Convolutional Neural Network (CNN) architectures, etc. Most of the recent research resulting in high accuracy face liveness detection and has focused on a two-step process of performing a speed diffusion, which is followed either by a Support Vector Machine (SVM) as a classifier [ 2 ], or a deep CNN architecture [ 3 , 4 ]. Existing approaches that have been proposed to address dynamic face spoofing attacks on recorded videos are based on methods such as texture analysis, motion analysis, image quality, and 3D structure information.…”

Section: Introductionmentioning

confidence: 99%

Enhanced Deep Learning Architectures for Face Liveness Detection for Static and Video Sequences

Koshy

Mahmood

2020

Self Cite

Face liveness detection is a critical preprocessing step in face recognition for avoiding face spoofing attacks, where an impostor can impersonate a valid user for authentication. While considerable research has been recently done in improving the accuracy of face liveness detection, the best current approaches use a two-step process of first applying non-linear anisotropic diffusion to the incoming image and then using a deep network for final liveness decision. Such an approach is not viable for real-time face liveness detection. We develop two end-to-end real-time solutions where nonlinear anisotropic diffusion based on an additive operator splitting scheme is first applied to an incoming static image, which enhances the edges and surface texture, and preserves the boundary locations in the real image. The diffused image is then forwarded to a pre-trained Specialized Convolutional Neural Network (SCNN) and the Inception network version 4, which identify the complex and deep features for face liveness classification. We evaluate the performance of our integrated approach using the SCNN and Inception v4 on the Replay-Attack dataset and Replay-Mobile dataset. The entire architecture is created in such a manner that, once trained, the face liveness detection can be accomplished in real-time. We achieve promising results of 96.03% and 96.21% face liveness detection accuracy with the SCNN, and 94.77% and 95.53% accuracy with the Inception v4, on the Replay-Attack, and Replay-Mobile datasets, respectively. We also develop a novel deep architecture for face liveness detection on video frames that uses the diffusion of images followed by a deep Convolutional Neural Network (CNN) and a Long Short-Term Memory (LSTM) to classify the video sequence as real or fake. Even though the use of CNN followed by LSTM is not new, combining it with diffusion (that has proven to be the best approach for single image liveness detection) is novel. Performance evaluation of our architecture on the REPLAY-ATTACK dataset gave 98.71% test accuracy and 2.77% Half Total Error Rate (HTER), and on the REPLAY-MOBILE dataset gave 95.41% accuracy and 5.28% HTER.