• We propose ABG-NAS, an adaptive NAS framework for graph representation learning. • A novel genetic search strategy dynamically balances exploration and exploitation. • Bayesian optimization is embedded to tune hyperparameters during the search process. • Our method outperforms SOTA GNAS methods on four benchmark graph datasets. • ABG-NAS achieves high F1 scores on both sparse and dense real-world graph structures. Effective and efficient graph representation learning is essential for enabling critical downstream tasks, such as node classification, link prediction, and subgraph search. However, existing graph neural network (GNN) architectures often struggle to adapt to diverse and complex graph structures, limiting their ability to produce structure-aware and task-discriminative representations. To address this challenge, we propose ABG-NAS, a novel framework for automated graph neural network architecture search tailored for efficient graph representation learning. ABG-NAS encompasses three key components: a Comprehensive Architecture Search Space (CASS), an Adaptive Genetic Optimization Strategy (AGOS), and a Bayesian-Guided Tuning Module (BGTM). CASS systematically explores diverse propagation ( P ) and transformation ( T ) operations, enabling the discovery of GNN architectures capable of capturing intricate graph characteristics. AGOS dynamically balances exploration and exploitation, ensuring search efficiency and preserving solution diversity. BGTM further optimizes hyperparameters periodically, enhancing the robustness and scalability of the resulting architectures to both large-scale graphs and high-complexity models. Empirical evaluations on benchmark datasets (Cora, PubMed, Citeseer, and CoraFull) demonstrate that ABG-NAS consistently outperforms both manually designed GNNs and state-of-the-art neural architecture search (NAS) methods. These results highlight the potential of ABG-NAS to advance graph representation learning by providing adaptive solutions that scale effectively across varying graph sizes and architectural complexities. Our code is publicly available at https://github.com/sserranw/ABG-NAS .

Recent work has explored federated clustering and developed an efficient k-means based method. However, it is well known that k-means clustering underperforms in high-dimensional space due to the so-called "curse of dimensionality". In addition, high-dimensional data (e.g., generated from healthcare, medical, and biological sectors) are pervasive in the big data era, which poses critical challenges to federated clustering in terms of, but not limited to, clustering effectiveness and communication efficiency. To fill this significant gap in federated clustering, we propose a one-shot federated subspace clustering scheme Fed-SC that can achieve remarkable clustering effectiveness on high-dimensional data while keeping communication cost low using only one round of communication for each local device. We further establish theoretical guarantees on the clustering effectiveness of one-shot Fed-SC and exploit the benefits of statistical heterogeneity across distributed data. Extensive experiments on synthetic and real-world datasets demonstrate significant effectiveness gains of Fed-SC compared with both subspace clustering and one-shot federated clustering methods.

Task-oriented communications, mostly using learning-based joint source-channel coding (JSCC), aim to design a communication-efficient edge inference system by transmitting task-relevant information to the receiver. However, only transmitting task-relevant information without introducing any redundancy may cause robustness issues in learning due to the channel variations, and the JSCC which directly maps the source data into continuous channel input symbols poses compatibility issues on existing digital communication systems. In this paper, we address these two issues by first investigating the inherent tradeoff between the informativeness of the encoded representations and the robustness to information distortion in the received representations, and then propose a task-oriented communication scheme with digital modulation, named discrete task-oriented JSCC (DT-JSCC), where the transmitter encodes the features into a discrete representation and transmits it to the receiver with the digital modulation scheme. In the DT-JSCC scheme, we develop a robust encoding framework, named robust information bottleneck (RIB), to improve the communication robustness to the channel variations, and derive a tractable variational upper bound of the RIB objective function using the variational approximation to overcome the computational intractability of mutual information. The experimental results demonstrate that the proposed DT-JSCC achieves better inference performance than the baseline methods with low communication latency, and exhibits robustness to channel variations due to the applied RIB framework.

Edge computing has recently garnered significant interest in many Internet of Things (IoT) applications. However, the excessive overhead during data exchange still remains an open challenge, especially for large-scale data processing tasks. This paper considers a master-aided distributed computing system with multiple edge computing nodes and a master node, where the master node helps edge nodes compute output functions. We propose a coded scheme to reduce the communication latency by exploiting computation and communication capabilities of all nodes and creating coded multicast opportunities. More importantly, we prove that the proposed scheme is always optimal, i.e., achieving the minimum communication latency, for arbitrary computing and storage abilities at the master. This extends the previous optimality results in the extreme cases (either the master could compute all input files or compute nothing) to the general case. Finally, numerical results and TeraSort experiments demonstrate that our schemes can greatly reduce the communication latency compared with the existing schemes.

Coexploitation behavior, referring to multiple software vulnerabilities being exploited jointly by one or more exploits, brings enormous challenges to the prevention and remediation of cyberattacks. Leveraging the latest advances in graph-driven intelligence, this article formulates vulnerability coexploitation behavior discovery as a link prediction problem between vulnerability entities within a vulnerability knowledge graph. We propose a modality-aware graph convolutional network (MAGCN) module to embed multimodality entity attributes and topological graph connectivity features into a unified lower dimensional feature space to boost link prediction performance. We further design a graph knowledge transfer learning (GKTL) strategy to transfer knowledge between subgraphs extracted from the same knowledge graph. Experimental results on a real-world dataset containing coexploitation incidents between 1995 and 2021 show that MAGCN achieved 81.34% on theF1 score when applying the GKTL strategy, superior to other graph neural network modules, such as GCN, GraphSAGE, EdgeGCN, and GINGCN.

As an increasingly prevalent technology in intelligent autonomous transportation systems, autonomous vehicle platoon has been indicated the ability to significantly reduce fuel consumption as well as heighten highway safety and throughput. However, existing efforts rarely focus on protecting data confidentiality and authenticity in autonomous vehicle platoons. How to ensure secure and high-fidelity platoon-level communication is still in its infancy. This paper makes the first attempt for efficient and secure communication across autonomous vehicle platoons. Specifically, we presentPDSM-FC, the first privacy-preserving data share mechanism with flexible cross-domain authorization over distinctive platoons. The key insight ofPDSM-FCis the design of a new ciphertext conversion technique, which allows a ciphertext to be easily converted into another type of ciphertext, facilitating efficient access by all entities holding the legitimate authorization. As a result,PDSM-FCcan achieve high-fidelity data communication between two unique platoons in ciphertext, so as to complete specific tasks including platoon integration. Rigorous security analysis shows thatPDSM-FCis secure against various attacks such as collusion, forgery and chosen-plaintext attacks. Moreover, theoretical evaluation and extensive experiments demonstrate the practicability ofPDSM-FCin terms of functionality, storage and computation overheads.

Long sequence time-series forecasting has become a central problem in multivariate time-series analysis due to its difficulty of consistently maintaining low prediction errors. Recent research has concentrated on developing large deep learning frameworks such as Informer and SCINet with remarkable results. However, these complex approaches were not benchmarked with simpler statistical methods and hence this part of the puzzle is missing for multivariate long sequence time-series forecasting (MLSTF). We investigate two simple statistical methods for MLSTF and provide analysis to indicate that linear regression owns a lower upper bound of error than deep learning methods and SNaive can act as an effective nonparametric method with unpredictable trends. Evaluations across six real-world datasets demonstrate that linear regression and SNaive are able to achieve state-of-the-art performance for MLSTF.

The expeditious development in cloud-enabled industrial Internet of Things (IIoT) healthcare has significantly reduced the costs to monitor and protect people at home while notably improving the quality of human healthcare. Despite its considerable convenience and benefits, it confronts some security and privacy challenges in the aspects of bilateral fine-grained access control, the authenticity and tamper resistance of shared health data. To tackle these constraints, a secure privacy-preserving bilateral access control scheme with fine granularity (PBAC-FG) is proposed in this article. Our PBAC-FG exploits fine-grained access control and matchmaking encryption technologies to ensure both participants (e.g., patients and healthcare providers) can specify their respective fine-grained access control over the encrypted health data, such that only authorized counterparts can efficiently access the health data. Besides, the correct rigorous security proofs are indicated to verify that our PBAC-FG is indeed secure. We carry out comprehensive performance evaluations and comparisons to demonstrate the efficiency and practicality of the PBAC-FG for IIoT healthcare applications.

The emerging of healthcare Industrial Internet of Things (HealthIIoT) cannot only facilitate high-quality care services for patients but also enable efficient telemedicine platform for healthcare practitioners. However, it faces several fundamental security and privacy challenges, such as secure fine-grained data delivery, privacy preserving keyword-based ciphertext retrieval, malicious key delegation, and efficiency of the system. To combat these issues, we propose a privacy-aware and traceable fine-grained system (PTFS) for secure data delivery in cloud-assisted HealthIIoT. Compared to the existing solutions that only implement some of the preceding features, the proposed solution enables secure fine-grained data delivery, privacy-preserving data retrieval, efficient encryption and decryption operations, and trace of malicious key delegation simultaneously. For security analysis, rigorous proofs of the proposed scheme are provided to prove its security. In addition, extensive simulations and experiments are conducted for performance evaluation, which demonstrate the feasibility and effectiveness of PTFS.

With an ever-accelerating trend of cybercrimes due to software vulnerabilities and exposures in Smart City industrial environment, effective and proactive vulnerability risk management becomes imperative. Statistical models learning rich historical vulnerability disclosure data undoubtedly provide critical risk insights. In this article, based on extreme value theory coupled with generalized additive models, we propose a novel framework to model extreme vulnerability disclosure events under both stationary and nonstationary scenarios. By utilizing this rigorous framework, we initiated an important study on quantifying extreme cyber risks. Through extensive empirical studies using real-life datasets, our proposed framework proves to effectively capture the dynamics of extreme events. Furthermore, it enables us to address quantitatively some of the key cyber risk management questions.

Due to the high temporal uncertainty and low signal-to-noise ratio, transfer learning for univariate time series forecasting remains a challenging task. In addition, data scarcity, which is commonly encountered in business forecasting, further limits the application of conventional transfer learning protocols. In this work, we have developed, DATSING, a transfer learning-based framework that effectively leverages cross-domain time series latent representations to augment target domain forecasting. In particular, we aim to transfer domain-invariant feature representations from a pre-trained stacked deep residual network to the target domains, so as to assist the prediction of each target time series. To effectively avoid noisy feature representations, we propose a two-phased framework which first clusters similar mixed domains time series data and then performs a fine-tuning procedure with domain adversarial regularization to achieve better out-of-sample generalization. Extensive experiments with real-world datasets have demonstrated that our method significantly improves the forecasting performance of the pre-trained model. DATSING has the unique potential to empower forecasting practitioners to unleash the power of cross-domain time series data.

Complex Big Data systems in modern organisations are progressively becoming attack targets by existing and emerging threat agents. Elaborate and specialised attacks will increasingly be crafted to exploit vulnerabilities and weaknesses. With the ever-increasing trend of cybercrime and incidents due to these vulnerabilities, effective vulnerability management is imperative for modern organisations regardless of their size. However, organisations struggle to manage the sheer volume of vulnerabilities discovered on their networks. Moreover, vulnerability management tends to be more reactive in practice. Rigorous statistical models, simulating anticipated volume and dependence of vulnerability disclosures, will undoubtedly provide important insights to organisations and help them become more proactive in the management of cyber risks. By leveraging the rich yet complex historical vulnerability data, our proposed novel and rigorous framework has enabled this new capability. By utilising this sound framework, we initiated an important study on not only handling persistent volatilities in the data but also further unveiling multivariate dependence structure amongst different vulnerability risks. In sharp contrast to the existing studies on univariate time series, we consider the more general multivariate case striving to capture their intriguing relationships. Through our extensive empirical studies using the real world vulnerability data, we have shown that a composite model can effectively capture and preserve long-term dependency between different vulnerability and exploit disclosures. In addition, the paper paves the way for further study on the stochastic perspective of vulnerability proliferation towards building more accurate measures for better cyber risk management as a whole.

Providing energy-efficient continuous data collection services is of paramount importance to Wireless Sensor Network (WSN) applications. This paper proposes a new power management framework called Data-Driven Power Management (DDPM) as the infrastructure for integrating various energy efficient techniques, such as the approximate querying and the sleep scheduling. By utilizing the beneficial properties of these techniques, we can achieve better energy efficiency while still meeting the application specific criteria, such as data accuracy and communication latency. The distinguishing feature of DDPM is that it starts by exploiting the natural tradeoff between the quality of the sensor data and the energy consumption, and then it generates a precision-guaranteed estimation for each sensor node as its maximum sleep time. Eventually deterministic schedules can be made by the DDPM based on these estimations. We further propose two decentralized algorithms so that the undesirable communication delays caused by staggered local sleep schedules can be avoided. The experimental results show that the nodespsila sleep times can be significantly increased while incurring only a minor rise in latency.

In this paper, we address one of the wireless sensor network (WSN) management problems - optimization on the execution of multiple commands. The objective of the paper is to provide efficient support for pre-processing a set of commands before disseminating into the sensor network. It is important that only necessary work will be assigned to the sensor network by virtue of strict energy constraint. The problem is NP-hard. We divide the problem into a series of tractable sub-problems along with their solutions. We present a novel hierarchical quadrant-based field partition mechanism to virtually divide the sensor field. We also classify and model WSN management commands. We then identify merging possibilities for a given command, which results in several merging rules and constraints. Lastly, we evaluate a simulated annealing based search algorithm for finding optimal merge order. The results show that energy can be significantly saved within short time-delay while the overall effects of the final command set still satisfies the users' requirements.