ABSTRACT
Abstract. Internet of Things (IoT) plays an important role in smart grids. Software-Defined Internet of Things (SD-IoT) employs the Software-Defined Networking (SDN) as the network architecture of IoT in smart grids. Hence, in smart grids, SD-IoT can achieve flexible network management using the network programmability. Nevertheless, IoT devices in smart grids face a number of security issues. The Low-rate Distributed Denial of Service (DDoS) is one of such a security issue. Detecting LDDoS is one of the most important steps in defending LDDoS. When detecting LDDoS in SD-IoT, a large number of network features are useless or even have side effects on the detection of LDDoS. Therefore, how to choose the feature subset from all features to improve the LDDoS detection performance is a key problem. In order to solve these problems, in this work, we propose ENTER, a multi-correlation information EA-based feature selection method, used to detect LDDoS for SD-IoT in smart grids. ENTER calculates the multi-correlation information of different individuals and adjusts the partial variation of the population through the multi-correlation information. ENTER is consisted of a novel multi-correlation information-based gene mutation strategy and a novel local optimum bounce strategy. The evaluation results indicate that ENTER can achieve high feature compression ratio while improve the detection performance of the LDDoS detector, in terms of detection precision, accuracy, recall, f-score and detection time.
- Cui Y, (2021). Towards DDoS detection mechanisms in software-defined networking. Journal of Network and Computer Applications.190.Google ScholarDigital Library
- Tang D, (2021). Performance and features: Mitigating the low-rate TCP-targeted DoS attack via SDN. IEEE Journal on Selected Areas in Communications 40(1):428-444.Google ScholarDigital Library
- Mafarja M, (2020). Augmented whale feature selection for IoT attacks: Structure, analysis and applications. Future Generation Computer Systems. 112:18-40.Google ScholarCross Ref
- Roopak M, (2020). Multi-objective-based feature selection for DDoS attack detection in IoT networks . IET Networks. 9(3):120-127.Google ScholarDigital Library
- Haddadpajouh H, (2020). A multikernel and metaheuristic feature selection approach for IoT malware threat hunting in the edge layer. Internet of Things Journal. 8(6):4540-4547.Google ScholarCross Ref
- Galeano-Brajones J, (2020). Detection and mitigation of DoS and DDoS attacks in IoT-based stateful SDN: An experimental approach. Sensors. 20(3).Google Scholar
- Javeed D, (2021). SDN-enabled hybrid DL-driven framework for the detection of emerging cyber threats in IoT. Electronics. 10(8).Google Scholar
- Thorat P, (2021).SDN-based predictive alarm manager for security attacks detection at the IoT gateways. IEEE Consumer Communications & Networking Conference (CCNC). 1-2.Google ScholarDigital Library
- Segura G A N, (2021).Distributed DoS Attack Detection in SDN: Tradeoffs in Resource Constrained Wireless Networks. Statistical Signal Processing Workshop (SSP). 131-135.Google Scholar
- Krishnan P, (2021). MUD-based behavioral profiling security framework for software-defined IoT networks[J]. IEEE Internet of Things Journal. 9(9): 6611-6622.Google ScholarCross Ref
- Singh A K, (2023). A secure elliptic curve based anonymous authentication and key establishment mechanism for IoT and cloud[J]. Multimedia Tools and Applications. 82(15): 22525-22576.Google ScholarDigital Library
- Anitha T, (2023) A novel methodology for malicious traffic detection in smart devices using BI-LSTM–CNN-dependent deep learning methodology[J]. Neural Computing and Applications. 1-20.Google Scholar
- Rafique W, (2019). CFADefense: A security solution to detect and mitigate crossfire attacks in software-defined IoT-edge infrastructure. High Performance Computing and Communications; Smart City; Data Science and Systems (HPCC/Smart City/DSS). 500-509.Google Scholar
- Sivanathan A, (2017). Characterizing and classifying IoT traffic in smart cities and campuses. Computer Communications Workshops (INFOCOM WKSHPS). 559-564.Google ScholarCross Ref
- Li T, (2019). Binary differential evolution based on individual entropy for feature subset optimization. IEEE access. 7: 4109-24121.Google ScholarCross Ref
- Asilian Bidgoli A, (2019). Opposition-based multi-objective binary differential evolution for multi-label feature selection. Evolutionary Multi-Criterion Optimization: 10th International Conference, Springer International Publishing. 553-564.Google ScholarCross Ref
Recommendations
Anomaly Detection in Smart Grids based on Software Defined Networks
SMARTGREENS 2019: Proceedings of the 8th International Conference on Smart Cities and Green ICT SystemsSoftware-defined networking (SDN) is a networking architecture that increasingly receives attention from power grid operators. The basic principle is the separation of the packet forwarding data plane and the central controller implemented in software ...
Vulnerability retrospection of security solutions for software-defined Cyber–Physical System against DDoS and IoT-DDoS attacks
AbstractThe wide dispersion of the Internet of Things (IoT), Software-defined Networks and Cloud Computing have given the wings to Cyber–Physical System adoption. The newfangled society relies so much on Cyber–Physical Systems, such as Smart ...
Robust Anomaly based Attack Detection in Smart Grids under Data Poisoning Attacks
CPSS '22: Proceedings of the 8th ACM on Cyber-Physical System Security WorkshopAnomaly-based attack detection methods are often used to detect data integrity or data falsification attacks in advanced metering infrastructure (AMI) of smart grids. However, there is a lack of studies on the effect of data poisoning attacks against ...
Comments