Chunyu Miao

The extremely destructive nature of malware has become a major threat to Internet security. The research on malware detection techniques has been evolving. Deep learning-based malware detection methods have achieved good results by using large-scale, pre-trained models. However, these models are complex, have large parameters, and require a large amount of hardware resources and have a high inference time cost when applied. To address this challenge, this paper proposes DistillMal, a new method for lightweight malware detection based on knowledge distillation, which improves performance by using a student network to learn valuable cueing knowledge from a teacher network to achieve a lightweight model. We conducted extensive experiments on two new datasets and showed that the student network model’s performance is very close to that of the original model and the outperforms it on some metrics. Our approach helps address the resource constraints and computational challenges faced by traditional deep learning large models. Our research highlights the potential of using knowledge distillation to develop lightweight malware detection models.

Link prediction, which aims to infer missing edges or predict future edges based on currently observed graph connections, has emerged as a powerful technique for diverse applications such as recommendation, relation completion, etc. While there is rich literature on link prediction based on node representation learning, direct link embedding is relatively less studied and less understood. One common practice in previous work characterizes a link by manipulate the embeddings of its incident node pairs, which is not capable of capturing effective link features. Moreover, common link prediction methods such as random walks and graph auto-encoder usually rely on full-graph training, suffering from poor scalability and high resource consumption on large-scale graphs. In this paper, we propose Inductive Subgraph Embedding for Link Prediciton (SE4LP) — an end-to-end scalable representation learning framework for link prediction, which utilizes the strong correlation between central links and their neighborhood subgraphs to characterize links. We sample the “link-centric induced subgraphs” as input, with a subgraph-level contrastive discrimination as pretext task, to learn the intrinsic and structural link features via subgraph classification. Extensive experiments on five datasets demonstrate that SE4LP has significant superiority in link prediction in terms of performance and scalability, when compared with state-of-the-art methods. Moreover, further analysis demonstrate that introducing self-supervision in link prediction can significantly reduce the dependence on training data and improve the generalization and scalability of model.

Localization is one of the most important technologies in wireless sensor networks. A lightweight distributed node localization scheme is proposed by considering the limited computational capacity of WSNs. The proposed scheme introduces the virtual force model to determine the location by incremental refinement. Aiming at solving the drifting problem and malicious anchor problem, a location verification algorithm based on the virtual force mode is presented. In addition, an anchor promotion algorithm using the localization reliability model is proposed to re-locate the drifted nodes. Extended simulation experiments indicate that the localization algorithm has relatively high precision and the location verification algorithm has relatively high accuracy. The communication overhead of these algorithms is relative low, and the whole set of reliable localization methods is practical as well as comprehensive.