Interactive image editing allows users to modify images through visual interaction operations such as drawing, clicking, and dragging. Existing methods construct such supervision signals from videos, as they capture how objects change with various physical interactions. However, these models are usually built upon text-to-image diffusion models, so necessitate (i) massive training samples and (ii) an additional reference encoder to learn real-world dynamics and visual consistency. In this paper, we reformulate this task as an image-to-video generation problem, so that inherit powerful video diffusion priors to reduce training costs and ensure temporal consistency. Specifically, we introduce FramePainter as an efficient instantiation of this formulation. Initialized with Stable Video Diffusion, it only uses a lightweight sparse control encoder to inject editing signals. Considering the limitations of temporal attention in handling large motion between two frames, we further propose matching attention to enlarge the receptive field while encouraging dense correspondence between edited and source image tokens. We highlight the effectiveness and efficiency of FramePainter across various of editing signals: it domainantly outperforms previous state-of-the-art methods with far less training data, achieving highly seamless and coherent editing of images, \eg, automatically adjust the reflection of the cup. Moreover, FramePainter also exhibits exceptional generalization in scenarios not present in real-world videos, \eg, transform the clownfish into shark-like shape. Our code will be available at https://github.com/YBYBZhang/FramePainter.

Emerging technologies such as artificial intelligence and big data have made numerous Internet of things (IoT) applications possible. In particular, the Artificial Intelligence of Things (AIoT) has the potential to promote the digitization and intelligent connection of all things. However, the openness and diversity of AIoT makes data information vulnerable to security attacks which can lead to a disruption of mobile communication networks. The complexity of real-time data security events requires accurate prediction of AIoT security performance. In this paper, a secure communication system model based on decode-and-forward (DF) relaying is proposed and its security performance is analyzed. Expressions for the secrecy outage probability (SOP) are derived, and these are used to evaluate the security performance. For this purpose, an intelligent SOP prediction algorithm based on MS-Net is proposed. MobileNet and SqueezeNet networks are used to design an improved lightweight MS-Net model, which is composed of a depth separable convolution block and a fire module in parallel. The fire module is used to reduce the number of parameters in the first branch, and the depth-separable convolution block is employed in the second branch instead of the standard convolution. This can adapt to nonlinear characteristic in the AIoT safety data and reduce energy consumption. Afterwards, the convolutional block attention module(CBAM) attention mechanism is used to improve the model’s ability to capture features. The proposed algorithm provides better AIoT security performance than other algorithms. In particular, the mean squared error (MSE) is 68.1% better than that of RegNet.

The explosive growth of Internet of Vehicle (IoV) applications has made information security a significant issue. Mobile IoV users are dynamic and the communication environment is very complex, which makes it very difficult to guarantee real-time secrecy communication performance. Thus, a reliable and effective evaluation and prediction of secrecy performance is critical. In this article, we have derived novel expressions for secrecy performance. A grey wolf optimization generalized regression (GWO-GR) algorithm is proposed to predict the secrecy performance and carry out the secrecy performance assessment. A generalized regression (GR) neural network is designed. Out of the input and output layers, the proposed GR network has a pattern layer and a summation layer, which can obtain a global convergence of network results. To further optimize the GR network, the grey wolf optimization algorithm is used to obtain the best spread factor for it, which can accelerate its rapid convergence. Through the simulated numerical results, we can obtain: 1) the proposed GWO-GR prediction algorithm is shown to provide better performance prediction results than other machine-learning-based methods; 2) in particular, the prediction accuracy is improved by 17.7%; and 3) the execution time has an 88.9% reduction.

The integration of artificial intelligence and Internet of Things (IoT) has promoted the rapid development of artificial IoT (AIoT) networks. A wide range of AIoT applications have generated a great deal of data. The fifth-generation (5G) mobile communication has powerful data processing capabilities, and it is a key technology to enable AIoT big data processing. The explosive growth of the 5G users has made information security in AIoT networks a significant issue. Real-time security evaluation in AIoT networks is difficult due to user mobility and dynamic wireless environments. Thus, the evaluation and prediction of secrecy performance is a very critical research. In this article, new expressions for the nonzero secrecy capacity probability (NSCP) are derived to evaluate the mobile collaborative secrecy performance. An improved convolutional neural network (CNN) model, named as SI-CNN in this article, is proposed to predict the NSCP performance. The SI-CNN model combines the SqueezeNet and InceptionNet, and it has four convolution layers, which all adopt the same convolution model. For the first two layers, they employ a 2 × 1 convolution and a three-branch convolution, which not only increase the number of channels but also extract more features. For the last two layers, they employ the same structure, but different convolution kernels. The proposed SI-CNN prediction algorithm is shown to provide better NSCP performance prediction than other state-of-the-art methods. In particular, compared with wavelet neural network, the prediction precision of SI-CNN is improved by 26.8%.

The global healthcare industry and artificial intelligence have promoted the development of the diversified intelligent healthcare applications. Internet of Things (IoT) will play an important role in meeting the high throughput requirements of diversified intelligent healthcare applications. However, the mobile IoT-enabled healthcare networks are diverse and open, the healthcare big data transmission is vulnerable to a potential attack, which can cause network outages and serious healthcare security issues. To process the complex healthcare security event in real time, security performance prediction is critical for mobile IoT-enabled healthcare networks. In this article, we first analyze the security performance, and derive the novel expressions for the security performance in a closed form. Then, to analyze the security performance in real time, a security performance intelligent prediction algorithm is proposed. An improved convolutional neural network (CNN) model is designed, which combines the four-layer convolution and a four-branch inception block, and can adopt different convolution kernels in the same layer. The four-branch inception block can increase the width of the CNN while reducing the parameters. The improved CNN model can not only increases the width of the CNN, extract different sizes of healthcare data features, but also increases the adaptability to the nonlinear healthcare big data. Compared with different methods, the proposed intelligent algorithm can obtain better security performance prediction. In particular, for prediction precision, the proposed intelligent algorithm is increased by 20%.

Industry 5.0 has developed in full swing, and accelerated the process of the sixth-generation (6G) mobile communication. Physical layer security is important for complex 6G mobile communication networks. To process active complex events in 6G mobile cooperative networks, predicting secrecy performance in time is essential for the mobile communication quality evaluation. Using amplify-and-forward (AF) relaying, we propose a transmit antenna selection (TAS) based secrecy scheme in this article. To analyze the security of 6G mobile cooperative networks, signal-to-noise ratio of the end-to-end link is used to derive the novel expressions for secrecy outage probability (SOP). The theoretical results are confirmed by simulation results. Then, we use SOP as the important merit to evaluate the secrecy performance, and set up the dataset. To achieve secrecy performance prediction, a convolutional neural network (CNN) based SOP prediction algorithm is proposed. The designed CNN model has five convolution layers, which all use the same convolution in the padding and do not change data size. For this improved CNN structure, we adopt the idea of SqueezeNet, which belongs to the lightweight CNN. The improved CNN model can greatly reduce the parameters and network complexity on the premise of ensuring the prediction accuracy. We also examine the following state-of-the-art techniques, first, Elman, second, InceptionNet, third, deep neural network (DNN), and fourth, support vector machine methods. The proposed CNN algorithm can achieve better SOP prediction results than other existing methods. In particular, compared with DNN method, the prediction accuracy is increased by 66.7%.

With the help of the new generation information technology, the Internet of Vehicle (IoV) networks have become widespread. IoV can improve the automatic driving ability, and provide users with intelligence, comfort, safety, energy saving and efficiency traffic services. However, the IoV networks face serious challenges due to the complex wireless environment. The vehicles cannot obtain the real-time traffic condition and early warning information, which leads to the decrease of link quality and the failure of information transmission. To evaluate the communication quality of IoV networks, the outage probability (OP) is commonly employed as a metric. This paper considers mobile IoV networks, and investigates communication quality prediction. Novel OP expressions are derived, which can analyze the OP performance. Then, to predict OP in real time, an intelligent OP prediction approach with an Elman model is proposed. This is evaluated with data generated using the OP expressions. In terms of computational complexity and prediction accuracy, the results obtained show that the Elman-based approach provides better forecasting effect than other methods. For prediction accuracy, the proposed Elman approach is increased by 84.6%. For computational complexity, the execution time is reduced by 79.9%.