Semantic communication, an emerging AI-driven communication paradigm, offers great potential for multimodal data delivery in space-ground integrated networks (SGINs). However, the dynamic nature of SGINs presents severe challenges for path selection, making it difficult to ensure the quality of service (QoS) at the semantic level. To this end, we propose in this paper a novel path selection scheme in space-ground multimodal semantic communication networks based on the sleeping multi-armed bandit (MAB) approach. Specifically, we first model the approximate semantic entropy and semantic rate, formulating an optimal path selection problem that integrates link state information and semantic data transmission volume. Then, we convert the path selection problem into a sleeping MAB problem and meticulously design an upper confidence bound (UCB)-based algorithm to solve it, called Periodic Probability Sleeping Path Selection (PPSPS), which copes with the dynamic feature of SGINs. We further theoretically verify the bounded regret of the PPSPS algorithm, indicating that it can ensure good semantic communication QoS. Simulation results demonstrate the superiority of the proposed path selection scheme compared to traditional reinforcement learning methods.

Crowdsourcing has attracted much attention for its convenience to collect labels from non-expert workers instead of experts. However, due to the high level of noise from the non-experts, a label aggregation model that infers the true label from noisy crowdsourced labels is required. In this article, we propose a novel framework based on graph neural networks for aggregating crowd labels. We construct a heterogeneous graph between workers and tasks and derive a new graph neural network to learn the representations of nodes and the true labels. Besides, we exploit the unknown latent interaction between the same type of nodes (workers or tasks) by adding a homogeneous attention layer in the graph neural networks. Experimental results on 13 real-world datasets show superior performance over state-of-the-art models.

Malicious Uniform Resource Locators (URLs) re-main one of the most common threats to cybersecurity. They are commonly spread through phishing, malware and spam. One popular way to detect malicious URLs is through black-lists. Blacklists maintain records of previously known malicious URL reputations. These lists are however shortcoming when there is need to detect newly generated malicious URLs. For that reason, modern research has resorted to training machine learning algorithms to detect malicious URLs. In this paper, we contributed towards the detection of malicious URLs using URL based features in a multiclass classification setting. We focused on three popular URL attack types which are phishing, spam and malware. Our work can be used as a supplementary tool in new or existing anti-phishing, anti-spam and anti-malware detection platforms. We compared the performance of the following ensemble learners: Extreme Gradient Boosting (XGBoost), Adaptive Boosting (AdaBoost), Light Gradient Boosting (LightGBM) and Categorical Boosting (CatBoost). We evaluated the performance of some URL features that we referred to as our features. These included priority features like Kullback-Leibler Divergence (KL divergence), bag of words segmentation and other word-based features. Results showed that our features performed better when compared to experiments we conducted without our features. We trained these algorithms on 126 983 URLs from benchmark datasets and all four learners returned an overall accuracy above 0.95.

Evaluation of a document summarization system has been a critical factor to impact the success of the summarization task. Previous approaches, such as ROUGE, mainly consider the informativeness of the assessed summary and require human-generated references for each test summary. In this work, we propose to evaluate the summary qualities without reference summaries by unsupervised contrastive learning. Specifically, we design a new metric which covers both linguistic qualities and semantic informativeness based on BERT. To learn the metric, for each summary, we construct different types of negative samples with respect to different aspects of the summary qualities, and train our model with a ranking loss. Experiments on Newsroom and CNN/Daily Mail demonstrate that our new evaluation method outperforms other metrics even without reference summaries. Furthermore, we show that our method is general and transferable across datasets.