With the increased demand for intelligence, neural networks have become an increasingly popular solution for intrusion detection systems (IDS), as their ability to learn complex patterns and behaviors makes them a suitable solution for distinguishing normal traffic from network intrusions. Hence, this paper proposes a new unsupervised IDS ensemble framework that utilizes parallel deep learning techniques based on three different anomaly detection concepts. That is, modeling the detection of point anomalies, collective anomalies, and contextual anomalies simultaneously.These detectors are trained in parallel, and the anomaly scores obtained from each detector are combined to provide the final detection decision. This ensemble approach can simultaneously consider the different types of anomalies in time series data and reduce the impact of overfitting some unsupervised anomaly detectors. Compared to supervised methods, the developed scheme reduces the overhead of manually annotated data and detects online possible novel attack data streams. The proposed ensemble model has been tested on the UNSW-NB15, DAPT 2020 and CSE-CIC-IDS 2018 datasets. Compared to baseline models, the single detectors used to constitute the ensemble model achieve better performance separately in most cases. Through three simple ensemble strategies, Vote, ‘And’ logic and ‘Or’ logic, the ensemble model exhibits improved stability, precision performance, and recall performance, respectively. This demonstrates that the proposed ensemble model can successfully combine the advantages of different unsupervised detectors, offering an advantage over other single unsupervised anomaly detection models. Moreover, the suggested method is effective for detecting various traffic anomalies caused by network intrusions that occur in the datasets.

Abstract Multi-source knowledge fusion is one of the important research topics in the fields of artificial intelligence, natural language processing, and so on. The research results of multi-source knowledge fusion can help computer to better understand human intelligence, human language and human thinking, effectively promote the Big Search in Cyberspace, effectively promote the construction of domain knowledge graphs (KGs), and bring enormous social and economic benefits. Due to the uncertainty of knowledge acquisition, the reliability and confidence of KG based on entity recognition and relationship extraction technology need to be evaluated. On the one hand, the process of multi-source knowledge reasoning can detect conflicts and provide help for knowledge evaluation and verification; on the other hand, the new knowledge acquired by knowledge reasoning is also uncertain and needs to be evaluated and verified. Collaborative reasoning of multi-source knowledge includes not only inferring new knowledge from multi-source knowledge, but also conflict detection, i.e. identifying erroneous knowledge or conflicts between knowledges. Starting from several related concepts of multi-source knowledge fusion, this paper comprehensively introduces the latest research progress of open-source knowledge fusion, multi-knowledge graphs fusion, information fusion within KGs, multi-modal knowledge fusion and multi-source knowledge collaborative reasoning. On this basis, the challenges and future research directions of multi-source knowledge fusion in a large-scale knowledge base environment are discussed.

Abstract In this paper, in order to simultaneously resolve the transmission security and availability in Supervisory Control And Data Acquisition (SCADA) group communications, we propose a robust and efficient group key management scheme, called LiSH+, which is characterized by developing a secure self‐healing mechanism witht‐revocation and collusion resistance capability. A dual direction hash chain is utilized to guarantee the backward secrecy and forward secrecy of group key. A novel self‐healing mechanism is constructed to ensure availability of the group member in case of devices failure and prevent the collusive users from exploiting the group key in the proposed scheme. In addition, the compromised users can be revoked from the group dynamically by broadcasting message. Detailed security analysis shows that the proposed LiSH+ scheme meets the requirements of group communication and is secure in terms oftuser collusion‐free. Performance evaluation also demonstrates its efficiency in terms of low storage requirement and communication overheads. Copyright © 2014 John Wiley & Sons, Ltd.

With extensive promising applications, machine to machine (M2M) communications or machine-type communication (MTC) have attached a tremendous interest among mobile network operators and research groups. Supporting multiple MTC devices has been considered as an essential requirement in M2M communications. How to achieve a secure and efficient access authentication for a group of MTC devices during roaming is a challenging issue. In this paper, in order to simultaneously resolve the access security and efficiency in MTC, we propose a secure and efficient group roaming scheme for MTC between 3GPP and WiMAX networks, named SEGR, which is characterized by authenticating all MTC devices in a group simultaneously and speeding up the process of authentication through adopting a novel certificateless aggregate signature technique. Through security analysis, the proposed SEGR can provide robust security, especially overcome the drawback of key escrow in identity-based (ID-based) aggregate signature schemes. In addition, performance evaluations in terms of communication overhead and computation complexity demonstrate that SEGR is more efficient than those traditional schemes.

Supevisory Control And Data Acquisition (SCADA) systems are vital for operation and control of critical infrastructures in smart grid. Availability is one of the most important security objectives in SCADA communications, unavailability of which may further undermine the power delivery, and a reliable key management is essential to address this problem. In this paper, in order to simultaneously resolve the transmission security and availability in SCADA group communications, we propose a robust and efficient group key management scheme, called LiSH, which is characterized by developing a secure self-healing mechanism with t-revocation capability using one-way function to protect current session keys from being attacked by intruders. Detailed security analysis shows that the proposed LiSH scheme is secure in terms of collusion-free, and t-wise forward and backward security. In addition, performance evaluation also demonstrates its efficiency in terms of low storage and communication overheads.

Supporting a massive number of machine-type communication (MTC) devices has been considered as an essential requirement in machine to machine (M2M) communications. Meanwhile, cyber security is of paramount importance in MTC; if MTC devices cannot securely access the networks through efficient authentication, all applications involving MTC cannot be widely accepted. One of research challenges in MTC is group authentication. A large number of MTC devices accessing the network simultaneously will cause a severe authentication signaling congestion. To solve this problem and reduce authentication overhead of the previous schemes based on public key cryptosystems, we propose a novel lightweight group authentication protocol for MTC in the long term evolution (LTE) networks based on aggregate message authentication codes (MACs), called LGTH, which can not only authenticate all MTC devices simultaneously, but also minimize the authentication overhead. Through security analysis, we conclude that the proposed LGTH can provide robust security, and avoid the authentication signaling congestion in the LTE networks. In addition, performance evaluations in terms of communication and computation overhead demonstrate that LGTH is more efficient than previous schemes.