Search

Deep network models rely on sufficient training samples to perform reasonably well, which has inevitably constrained their application in classification of hyperspectral images (HSIs) due to the limited availability of labeled data. To tackle this particular challenge, we propose a hybrid relation network, H-RNet, by combining three-dimensional (3-D) convolution neural networks (CNN) and two-dimensional (2-D) CNN to extract the spectral–spatial features whilst reducing the complexity of the network. In an end-to-end relation learning module, the sample pairing approach can effectively alleviate the problem of few labeled samples and learn correlations between samples more accurately for more effective classification. Experimental results on three publicly available datasets have fully demonstrated the superior performance of the proposed model in comparison to a few state-of-the-art methods. [ABSTRACT FROM AUTHOR]

With the rapid development of the Internet and information technology (in particular, generative adversarial networks and deep learning), network data are exploding. Due to the misuse of technology and inadequate supervision, deep-network-generated face images flood the network, and the forged image is called a deepfake. Those realistic faked images launched a serious challenge to the human eye and the automatic identification system, resulting in many legal, ethical, and social issues. For the needs of network information security, deep-network-generated face image identification based on different color spaces is proposed. Due to the extremely realistic effect of deepfake images, it is difficult to achieve high accuracy with ordinary methods for neural networks, so we used the image processing method here. First, by analyzing the differences in different color space components in the deep learning network model for face sensitivity, a combination of color space components that can effectively improve the discrimination rate of the deep learning network model is given. Second, to further improve the discriminative performance of the model, a channel attention mechanism was added at the shallow level of the model to further focus on the features contributing to the model. The experimental results show that this scheme achieved better accuracy in the same face generation model and in different face generation models than the two compared methods, and its accuracy reached up to 99.10% in the same face generation model. Meanwhile, the accuracy of this model only decreased to 98.71% when coping with a JPEG compression factor of 100, which shows that this model is robust. [ABSTRACT FROM AUTHOR]

In recent years, methods based on deep convolutional neural networks have made great progress in the field of image super-resolution reconstruction. However, mainstream approaches generally establish many network layers, leading to high computational costs and memory usage that are unsuitable for resource-limited edge devices. To alleviate this issue, a lightweight inverted residual attention network (IRAN) is proposed to obtain better super-resolution reconstruction performance with lower parameters and computation. The main structure of the IRAN consists of a series of inverted residual attention groups (IRAGs), which are mainly composed of several inverted residual attention blocks (IRABs). IRAB effectively reduces the network parameters and computation while extracting depth features by introducing the inverted residual structure and uses the simple channel attention mechanism to learn the important channel feature information. In addition, an enhanced spatial attention mechanism is introduced at the beginning and end of IRAG to further improve the reconstruction performance of the network. The experimental results show that compared with the mainstream lightweight networks, not only the peak signal-to-noise ratio and structural similarity of image quality metrics are better but also the parameters and the computational effort of the network are lower. [ABSTRACT FROM AUTHOR]

Due to the heavy reliance on computers and networks, security issues have become a major concern for individuals, companies, and nations. Traditional security measures such as personal identification numbers, tokens, or passwords only provide limited protection. With the development of intelligent keyboard (IKB), this paper proposes a deep‐learning‐based keystroke dynamics identification method for increased security. The IKB is a kind of self‐powered, nonmechanical‐punching keyboard, which converts mechanical stimuli applied to the keyboard into local electronic signals. Multilayer deep belief network (DBN) is established to mine the useful information from raw electronic signals and output the keystroke dynamics identification result. The contributions include development of a novel solution that does not rely on manual feature extraction, and provides promising recognition accuracy on large amount of typing samples. One significant advantage of the proposed method is that it extracts features adaptively from the raw current signals and automatically recognizes the typing pattern, which simplifies the design of verification and identification system. The experimental results on 104 typing samples demonstrate the effectiveness of the proposed method. The proposed method has extensive applications in keyboard‐based information security. A novel keystroke dynamics identification method is developed for intelligent keyboard using deep learning technologies. Experiment results on 104 typing datasets show that the proposed method has high identification accuracy, stable and reliable performance. [ABSTRACT FROM AUTHOR]