RETRACTED ARTICLE: Artificial intelligence enabled fuzzy multimode decision support system for cyber threat security defense automation

被引:0
作者
Feilu Hang
Linjiang Xie
Zhenhong Zhang
Wei Guo
Hanruo Li
机构
[1] Information Center of Yunnan Power Grid Co. Ltd,
来源
Journal of Computer Virology and Hacking Techniques | 2023年 / 19卷
关键词
Fuzzy; Multimode; Decision support; Security defense; Automation; Artificial intelligence; Attack; Decision-making;
D O I
暂无
中图分类号
学科分类号
摘要
Security defense automation uses technology that reduces human assistance to integrate security applications, processes, and infrastructure. In the process of defense and attack, there will be a period of delay in establishing the decision-making and strategy. Recently, fuzzy-based decision-making has been effectively utilized for uncertainty and vague data in security applications. Fuzzy decision tree blends fuzzy representation and associates approximate reasoning with symbolic decision trees. They provide for handling language-related uncertainty, noise, missing or faulty features, and robust behavior while also providing comprehensible knowledge interpretation. Cyber threat intelligence is information an organization utilizes to understand the dangers that have, might, and is presently attacking the company. The collection of single or multi-criteria techniques using fuzzy logic aiming at selecting the best alternative in case of inaccurate, incomplete, and vague information. Hence, this paper proposes a fuzzy multimode decision support system (FMMDSS) for security defense automation. Fuzzy logic is a progression to define the human inclination of accurate thinking that simplifies classical logic. This paper aims at the state explosion problem when network nodes increase and design the attack-defense graph to compress the state space and extract network states and defense policies. A simple example representing the suggested model to support decision-making accompanies the security attack and defense processes. This research will potentially offer new ideas and stimuli for future designs of network security and defense automation architecture. This paper concludes with a policy for implementing the recommended model in an operational setting with better dependability predictions, general comparison of predictive analysis ratio 89.7% and a cognitive ability ratio 92.5%, the security control selection ratio of 82.5%. Scalability ratios of 85.2% with an overall performance of 95.7% are measured using conventional methods and our proposed system.
引用
收藏
页码:257 / 269
页数:12
相关论文
共 90 条
[1]  
Gheisari M(2021)OBPP: an ontology-based framework for privacy-preserving in IoT-based smart city Futur. Gener. Comput. Syst. 123 1-13
[2]  
Najafabadi HE(2018)A hybrid whale optimization algorithm based on local search strategy for the permutation flow shop scheduling problem Futur. Gener. Comput. Syst. 85 129-145
[3]  
Alzubi JA(2015)A maximum-weight-independent-set-based algorithm for reader-coverage collision avoidance arrangement in RFID networks IEEE Sens. J. 16 1342-1350
[4]  
Gao J(2020)DITrust chain: towards blockchain-based trust models for sustainable healthcare IoT systems IEEE Access 8 111223-111238
[5]  
Wang G(2019)A group decision-making framework based on neutrosophic TOPSIS approach for smart medical device selection J. Med. Syst. 43 38-6615
[6]  
Abbasi AA(2020)Fingerprint enhancement based on the tensor of wavelet subbands for classification IEEE Access 8 6602-3321
[7]  
Castiglione A(2018)Distributed location and trust-based replica detection in wireless sensor networks Wirel. Pers. Commun. 102 3303-642
[8]  
Abdel-Basset M(2019)Feature selection based on artificial bee colony and gradient boosting decision tree Appl. Soft Comput. 74 634-282
[9]  
Manogaran G(2020)An interval-stochastic programming-based approach for a fully uncertain multi-objective and multimode resource investment project scheduling problem with an application to ERP project implementation Expert Syst. Appl. 149 113189-83
[10]  
El-Shahat D(2021)An intelligent human-unmanned aerial vehicle interaction approach in real-time based on machine learning using wearable gloves Sensors 21 1766-431