25 December 2020 in IEEE Transactions on Industrial Informatics
As a lightweight, flexible, and high-performance operating system virtualization, containers are used to speed up the big data platform. However, due to the imperfection of the resource isolation mechanism and the property of shared kernel, the meltdown and spectre attacks can lead to information leakage of kernel space and coresident containers. In this article, a noise-resilient and real-time detection system, named ContainerGuard, is proposed to detect meltdown and spectre attacks in the container-based big data platform. ContainerGuard uses a nonintrusive manner to collect lifecycle multivariate time-series performance event data of processes in containers and then uses ensemble of variational autoencoders as generative neural networks to learn the robust representations of normal patterns. Therefore, ContainerGuard meets the urgent need for information protection in the container-based big data platform. Our evaluations using real-world datasets show that ContainerGuard achieves excellent detection performance and only introduces about 4.5% of running performance overhead to the platform.
18 August 2019 in Security and Communication Networks
With the rapid development of Internet of things technology, the application of intelligent devices in the medical industry has become ubiquitous. Connected devices have revolutionized clinicians and patient care but also made modern hospitals vulnerable to cyber attacks. Among the security risks, botnets are of particular concern, which can be used to control thousands of devices for remote data theft and equipment destruction. In this paper, we propose a non-Markovian spread dynamics model to understand the effects of botnet propagation, which can characterize the hybrid contagion situation in reality. Based on the Susceptible-Adopted-Recovered model, we introduce nonredundant memory spread mechanism for global propagation, as a tuner to adjust spreading rate difference. For describing the proposed model, we extend a heterogeneous edge-based compartmental theory. Through extensive numerical simulations, we reveal that the growth pattern of the final adoption size versus the information transmission probability is discontinuous and how the final adoption size is affected by hybrid ratio α, global scope control factor ϵ, accumulated received information threshold T, and other parameters on ER network. Furthermore, we give the theory and simulation result on BA network and also compare the two hybrid methods—single infection in one time slice and double infections in one time slice—to evaluate the influence on final adoption size. We found in SIOT hybrid contagion scenario the final adoption size shows the phenomenon of a decline followed by an increase versus different hybrid ratio, and it is both verified in theory and numerical simulation. Through validation by thousands of experiments, our developed theory agrees well with the numerical simulations.
11 October 2022 in Security and Communication Networks
With the increasingly prominent value of big data, data sharing within enterprises and organizations has become increasingly popular, and many institutions have established data centers to achieve effective data storage and sharing. Meanwhile, cyberspace data security and privacy have become the most critical issue that people are concerned about since shared data often involves commercial secrets and sensitive information. At present, data encryption techniques have been applied to protect the security of the sensitive data stored in and shared by the data centers. However, the challenges of efficient data sharing, secure management of decryption keys, deduplication of the plaintext, and transparency and auditability of the data access arise. These challenges may obstruct the development of data sharing in data-driven systems. To meet these challenges, we propose a secure and trustworthy data sharing scheme and introduce blockchain, proxy re-encryption (PRE), and trusted execution environments (TEEs) into the data-driven systems. Our scheme mainly enables (1) automatic distribution and management of the decryption keys, (2) reduction of the reduplicative data, and (3) trustworthy data sharing and recording. Finally, we implement the proposed scheme and compare it with other existing schemes. It is demonstrated that our scheme reduces the computation and communication overhead.
26 August 2020 in Discrete Dynamics in Nature and Society
Opinion mining plays an important role in public opinion monitoring, commodity evaluation, government governance, and other areas. One of the basic tasks of opinion mining is to extract the expression elements, which can be further divided into direct subjective expression and expressive subjective expression. For the task of subjective expression extraction, the methods based on neural network can learn features automatically without exhaustive feature engineering and have been proved to be efficient for opinion mining. Constructing adequate input vector which can encode sufficient information is a challenge of neural network-based approach. To cope with this problem, a novel representation method that combines the different features with word vectors is proposed. Then, we use neural network and conditional random field to train and predict the expressions and carry out comparative experiments on different methods and features combinations. Experimental results show the performance of the proposed model, and the F value outperforms other methods in comparative experimental dataset. Our work can provide hint for further research on opinion expression extraction.
12 August 2019 in IEEE Access
The scale of mobile users for parallel access is constrained by the capacity of the base stations. When extremely dense terminal access exceeds the capacity of the base stations, access failure and a performance degradation will occur. The early detection and prediction of important events and the timely detection of possible large-scale terminal access are significant aspects in ensuring the quality of the communication achieved. For the automatic detection of events, methods based on a neural network can learn features automatically without feature engineering and have been proven to be efficient for event detection. As is well known, constructing an adequate input vector that can represent sufficient information is a challenge to a neural network-based approach, particularly for problems caused by Chinese word segmentation and too many unknown communication words. To cope with this problem, a novel representation method that combines the different features with word vectors is proposed to deal with the problem of Chinese event trigger identification. We then use a gated recurrent unit network to train and predict the event trigger and carry out comparative experiments on different methods and feature combinations. The experiment results of the proposed model show that the F1 value can reach 84% for the experimental dataset. Furthermore, the combination of lexical and syntactic features with a neural network was proven to be helpful for this task, although the contributions vary in magnitude for different features. Our study provides directions for further research on the use of lexical and syntactic features with a neural network for an event detection task.