Guoying Zhao’s research while affiliated with University of Oulu and other places

Active defense is an important approach to counter speech deepfakes that threaten individuals' privacy, property, and reputation. However, the existing works in this field suffer from issues such as time-consuming and ordinary defense effectiveness. This letter proposes a Generative Adversarial Network (GAN) framework for adversarial attacks as a defense against malicious voice conversion. The proposed method uses a generator to produce adversarial perturbations and adds them to the mel-spectrogram of the target audio to craft adversarial example. In addition, in order to enhance the defense effectiveness, a spectrogram waveform conversion simulation module (SWCSM) is designed to simulate the process of reconstructing waveform from the adversarial mel-spectrogram example and re-extracting mel-spectrogram from the reconstructed waveform. Experiments on four state-of-the-art voice conversion models show that our method achieves the overall best performance among five compared methods in both white-box and black-box scenarios in terms of defense effectiveness and generation time. The source code is available at GitHub by https://github.com/imagecbj/ Initiative-Defense-against-Voice-Conversion-through-Gen erative-Adversarial-Network.

Synthetic speech attacks bring more threats to Automatic Speaker Verification (ASV) systems, thus many synthetic speech detection (SSD) systems have been proposed to help the ASV system resist synthetic speech attacks. However, existing SSD systems still lack the generalization ability for the attacks generated by unknown synthesis algorithms. This paper proposes an end-to-end ensemble system, namely Dual-Branch Network, in which linear frequency cepstral coefficients (LFCC) and constant Q transform (CQT) are used as the input of two branches respectively. In addition, four fusion strategies are compared for the fusion of two branches to obtain an optimal one; multi-task learning and convolutional block attention module (CBAM) are introduced into the Dual-Branch Network to help the network learn the common forgery features from different forgery types of speech and enhance the representation power of learned features. Experimental results on the ASVspoof 2019 logical access (LA) dataset demonstrate that the proposed system outperforms existing state-of-the-art systems on both t-DCF and EER scores and has good generalization for unknown forgery types of synthetic speech. The source code is available at https://github.com/imagecbj/End-to-End-Dual-Branch-Network-Towards-Synthetic-Speech-Detection .</i

It has become a research hotspot to detect whether a video is natural or DeepFake. However, almost all the existing works focus on detecting the inconsistency in either spatial or temporal. In this paper, a dual-branch (spatial branch and temporal branch) neural network is proposed to detect the inconsistency in both spatial and temporal for DeepFake video detection. The spatial branch aims at detecting spatial inconsistency by the effective EfficientNet model. The temporal branch focuses on temporal inconsistency detection by a new network model. The new temporal model considers optical flow as input, uses the EfficientNet to extract optical flow features, utilize the Bidirectional Long-Short Term Memory (Bi-LSTM) network to capture the temporal inconsistency of optical flow. Moreover, the optical flow frames are stacked before inputting into the EfficientNet. Finally, the softmax scores of two branches are combined with a binary-class linear SVM classifier. Experimental results on the compressed FaceForensics++ dataset and Celeb-DF dataset show that: (a) the proposed dual-branch network model performs better than some recent spatial and temporal models for the Celeb-DF dataset and all the four manipulation methods in FaceForensics++ dataset since these two branches can complement each other; (b) the use of optical flow inputs, Bi-LSTM and dual-branches can greatly improve the detection performance by the ablation experiments.

With the development of face image synthesis and generation technology based on generative adversarial networks (GANs), it has become a research hotspot to determine whether a given face image is natural or generated. However, the generalization capability of the existing algorithms is still to be improved. Therefore, this paper proposes a general algorithm. To do so, firstly, the learning on important local areas, containing many face key‐points, is strengthened by combining the global and local features. Secondly, metric learning based on the ArcFace loss is applied to extract common and discriminative features. Finally, the extracted features are fed into the classification module to detect GAN‐generated faces. The experiments are conducted on two publicly available natural datasets (CelebA and FFHQ) and seven GAN‐generated datasets. Experimental results demonstrate that the proposed algorithm achieves a better generalization performance with an average detection accuracy over 0.99 than the state‐of‐the‐art algorithms. Moreover, the proposed algorithm is robust against additional attacks, such as Gaussian blur, and Gaussian noise addition.

Although the current generative adversarial networks (GAN)-generated face forensic detectors based on deep neural networks (DNNs) have achieved considerable performance, they are vulnerable to adversarial attacks. In this paper, an effective local perturbation generation method is proposed to expose the vulnerability of state-of-the-art forensic detectors. The main idea is to mine the fake faces’ areas of common concern in multiple-detectors’ decision-making, then generate local anti-forensic perturbations by GANs in these areas to enhance the visual quality and transferability of anti-forensic faces. Meanwhile, in order to improve the anti-forensic effect, a double- mask (soft mask and hard mask) strategy and a three-part loss (the GAN training loss, the adversarial loss consisting of ensemble classification loss and ensemble feature loss, and the regularization loss) are designed for the training of the generator. Experiments conducted on fake faces generated by StyleGAN demonstrate the proposed method’s advantage over the state-of-the-art methods in terms of anti-forensic success rate, imperceptibility, and transferability. The source code is available at https://github.com/imagecbj/A-Local-Perturbation-Generation-Method-for-GAN-generated-Face-Anti-forensics .

In recent years, generative adversarial networks (GANs) have been widely used to generate realistic fake face images, which can easily deceive human beings. To detect these images, some methods have been proposed. However, their detection performance will be degraded greatly when the testing samples are post-processed. In this paper, some experimental studies on detecting post-processed GAN-generated face images find that (a) both the luminance component and chrominance components play an important role, and (b) the RGB and YCbCr color spaces achieve better performance than the HSV and Lab color spaces. Therefore, to enhance the robustness, both the luminance component and chrominance components of dual-color spaces (RGB and YCbCr) are considered to utilize color information effectively. In addition, the convolutional block attention module and multilayer feature aggregation module are introduced into the Xception model to enhance its feature representation power and aggregate multilayer features, respectively. Finally, a robust dual-stream network is designed by integrating dual-color spaces RGB and YCbCr and using an improved Xception model. Experimental results demonstrate that our method outperforms some existing methods, especially in its robustness against different types of post-processing operations, such as JPEG compression, Gaussian blurring, gamma correction, and median filtering.