With the development of network technology, the number of gambling websites has grown dramatically, causing a threat to social stability. There are many machine learning-based methods are proposed to identify gambling websites by analyzing the URL, the text, and the images of the websites. Nevertheless, most of the existing methods ignore one important piece of information, i.e., the text within the website images. Only the visual features of images are extracted for detection, while the semantic features of texts on the images are ignored. However, these texts have key information clearly pointing to gambling websites, which can help us identify such websites more accurately. Therefore, how to fuse image and text multimodal data is a challenge that should be met.Motivated by this, in this paper, we propose a hybrid multimodal data fusion-based method for identifying gambling websites by extracting and fusing visual and semantic features of the website screenshots. First, we fine tune the pretrained ResNet34 model to train an image classifier and to extract visual features of webpage screenshots. Second, we extract textual content from webpage screenshots through the optical character recognition (OCR) technique. We use pretrained Word2Vec word vectors as the initial embedding layer and use Bi-LSTM to train a text classifier and extract semantic features of textual content on the screenshots. Third, we use self-attention to fuse the visual and semantic features and train a multimodal classifier. The prediction results of image, text, and multimodal classifiers are fused by the late fusion method to obtain the final prediction result. To demonstrate the effectiveness of the proposed method, we conduct experiments on the webpage screenshot dataset we collected. The experimental results indicate that OCR text on the webpage screenshots has strong semantic features and the proposed hybrid multimodal data fusion based method can effectively improve the performance in identifying gambling websites, with accuracy, precision, recall, and F1-score all over 99%.

Affected by various error factors in the actual environment, the accuracy of the direction of arrival (DOA) estimation algorithm will greatly decrease during an application. To address this issue, in this paper, we propose an intelligent DOA estimation error calibration method based on transfer learning, which learns error knowledge from a small number of actual signal samples and improves the DOA estimation accuracy in the real application. We constructed a deep convolutional neural network (CNN)-based intelligent DOA estimation model to learn the mapping between the input signals and their azimuths. We generated a large number of ideal simulation signal samples to train the CNN model and used it as the pretrained model. Then, we fine-tuned the CNN model with a small number of actual signal samples collected in the actual environment. We demonstrate the effectiveness of the proposed method through simulation experiments. The experimental results indicate that the proposed method can effectively improve the accuracy of DOA estimation in the actual environment.

A pseudorandom sequence is a repeatable sequence with random statistical properties that is widely used in communication encryption, authentication and channel coding. The pseudorandom sequence generator based on the linear feedback shift register has the problem of a fixed sequence, which is easily tracked. Existing methods use the secret linear feedback shift register (LFSR) and built-in multiple LFSRs and is difficult to prevent cracking based on the hardware analysis. Since the plaintext depends on a specific language to be generated, using pseudo-random sequence encryption, it faces the problem that the encryptor cannot hide the characteristics of the plaintext data. Fractal functions have the following properties: chaotic, unpredictable and random. We propose a novel pseudorandom sequence generator based on the nonlinear chaotic systems, which is constructed by the fractal function. Furthermore, we design a data processing matrix to hide the data characteristics of the sequence and enhance the randomness. In the experiment, the pseudo-random sequences generator passed 16 rigorous test items from the National Institute of Standards and Technology (NIST), which means that the nonlinear pseudorandom sequence generator for the fractal function is effective and efficient.

The emergence of illegal (gambling, pornography, and attraction) websites seriously threatens the security of society. Due to the concealment of illegal websites, it is difficult to obtain labeled data with high quantity. Meanwhile, most illegal websites usually disguise themselves to avoid detection; for example, some gambling websites may visually resemble gaming websites. However, existing methods ignore the means of camouflage in a single modality. To address the above problems, this paper proposes MEDAL, a multimodality-based effective data augmentation framework for illegal website identification. First, we established an illegal website identification framework based on tri-training that combines information from different modalities (including image, text, and HTML) while making full use of numerous unlabeled data. Then, we designed a multimodal mutual assistance module that is integrated with the tri-training framework to mitigate the introduction of error information resulting from an unbalanced single-modal classifier performance in the tri-training process. Finally, the experimental results on the self-developed dataset demonstrate the effectiveness of the proposed framework, performing well on accuracy, precision, recall, and F1 metrics.

With the quick development of network technology, the number of active IoT devices is growing rapidly. Numerous network scanning organizations have emerged to scan and detect network assets around the clock. This greatly facilitates illegal cyberattacks and adversely affects cybersecurity. Therefore, it is important to discover and identify network scanning organizations on the Internet. Motivated by this, we propose a network scanning organization discovery method based on a graph convolutional neural network, which can effectively cluster out network scanning organizations. First, we constructed a network scanning attribute graph to represent the topological relationship between network scanning behaviors and targets. Then, we extract the deep feature relationships in the attribute graph via graph convolutional neural network and perform clustering to get network scanning organizations. Finally, the effectiveness of the method proposed in this paper is experimentally verified with an accuracy of 83.41% for the identification of network scanning organizations.