Metaheuristic neural networks for anomaly recognition in industrial sensor networks with packet latency and jitter for smart infrastructures

Mansouri, Amin; Majidi, Babak; Shamisa, Abdolah

doi:10.1080/1206212x.2018.1533613

Cited by 18 publications

(11 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It can be noticed that our approach demonstrates considerably greater performance matched to the other methods. The models showing neighboring efficiency to our approach are the Bloom filter model, the Random Forest model, the AutoMLP [54] and the Feng et al [34] model. But, their anomaly detection ability is still noticeably inferior to ours.…”

Section: ) Rq2: Comparison With Other Modelsmentioning

confidence: 99%

“…In reply to the investigation question (RQ2), we match the effectiveness of the suggested approach with the stateof-the-art approaches [34], [52]- [54] in order to find out the efficiency enhancement of the projected approach. The comparison shows that our approach shows significant performance improvement in terms of accuracy over the benchmark models.…”

Section: A Research Questionsmentioning

confidence: 99%

“…These models are Gaussian Mixture Model (GMM) and Principal Component Analysis with Singular Value Decomposition method (PCA-SVD). The numbers for these two models are directly taken from [52], Feng et al [34], AutoMLP [54] and Demertzis et al [53]. To the best of our knowledge, these are the latest methods that could aid to forecast the intrusions in SCADA and has substantial results.…”

Section: ) Rq2: Comparison With Other Modelsmentioning

confidence: 99%

See 2 more Smart Citations

HML-IDS: A Hybrid-Multilevel Anomaly Prediction Approach for Intrusion Detection in SCADA Systems

Khan

et al. 2019

IEEE Access

111

View full text Add to dashboard Cite

Critical infrastructures, e.g., electricity generation and dispersal networks, chemical processing plants, and gas distribution, are governed and monitored by supervisory control and data acquisition systems (SCADA). Detecting intrusion is a prevalent area of study for numerous years, and several intrusion detection systems have been suggested in the literature for cyber-physical systems and industrial control system (ICS). In recent years, the viruses seismic net, duqu, and flame against ICS attacks have caused tremendous damage to nuclear facilities and critical infrastructure in some countries. These intensified attacks have sounded the alarm for the security of the ICS in many countries. The challenge in constructing an intrusion detection framework is to deal with unbalanced intrusion datasets, i.e. when one class is signified by a lesser amount of instances (minority class). To this end, we outline an approach to deal with this issue and propose an anomaly detection method for the ICS. Our proposed approach uses a hybrid model that takes advantage of the anticipated and consistent nature of communication patterns that occur among ground devices in ICS setups. First, we applied some preprocessing techniques to standardize and scale the data. Second, the dimensionality reduction algorithms are applied to improve the process of anomaly detection. Third, we employed an edited nearest-neighbor rule algorithm to balance the dataset. Fourth, by using the Bloom filter, a signature database is created by noting the system for a specific period lacking the occurrence of abnormalities. Finally, to detect new attacks, we combined our package contents-level detection with another instance-based learner to make a hybrid method for anomaly detection. The experimental results with a real large-scale dataset generated from a gas pipeline SCADA system show that the proposed approach HML-IDS outperforms the benchmark models with an accuracy rate of 97%. INDEX TERMS Bloom filters, zero-day attacks, intrusion detection, SCADA, industrial control systems.

show abstract

Section: ) Rq2: Comparison With Other Modelsmentioning

confidence: 99%

Section: A Research Questionsmentioning

confidence: 99%

Section: ) Rq2: Comparison With Other Modelsmentioning

confidence: 99%

See 1 more Smart Citation

HML-IDS: A Hybrid-Multilevel Anomaly Prediction Approach for Intrusion Detection in SCADA Systems

Khan

et al. 2019

IEEE Access

111

View full text Add to dashboard Cite

show abstract

“…It should be noted that the recommended IDS schemes in the current literature, including the ones discussed earlier involving data mining [42][43][44], machine learning [39,45], some form of artificial intelligence [46,47], or the like, are implemented in the sensors themselves, with the majority of them being specific-attack-based. Also, most of the authors comment on the small size of sensor batteries and memory space, but without much focus on the amelioration of the effects of the implemented security schemes on the efficiency and shelf life of the sensors involved, especially in terms of sensor memory space.…”

Section: Wireless Sensor Network' Vulnerabilities and Threatsmentioning

confidence: 99%

A Security Concept Based on Scaler Distribution of a Novel Intrusion Detection Device for Wireless Sensor Networks in a Smart Environment

Boni

Chen

et al. 2020

Sensors

View full text Add to dashboard Cite

Following the significant improvement of technology in terms of data collection and treatment during the last decades, the notion of a smart environment has widely taken an important pedestal in the science industry. Built in order to better manage assets, smart environments provide a livable environment for users or citizens through the deployment of sensors responsible for data collection. Much research has been done to provide security to the involved data, which are extremely sensitive. However, due to the small size and the memory constraint of the sensors, many of these works are difficult to implement. In this paper, a different concept for wireless sensor security in smart environments is presented. The proposed security system, which is based on the scaler distribution of a novel electronic device, the intrusion detection system (IDS), reduces the computational functions of the sensors and therefore maximizes their efficiency. The IDS also introduces the concept of the feedback signal and “trust table” used to trigger the detection and isolation mechanism in case of attacks. Generally, it ensures the whole network security through cooperation with other IDSs and, therefore, eliminates the problem of security holes that may occur while adopting such a security technique.

show abstract

“…The results of applying some classical machine learning algorithms (K-means, Naive Bayesian, GMM, PCA-SVD) are presented in [9] using the example of the Gas Pipeline dataset. Fully connected evolutionary based neural networks are used in [10] to detect anomalies. In particular, the Gray Wolf Optimize algorithm is used to increase the speed of network learning.…”

Section: Introductionmentioning

confidence: 99%

Applying methods of machine learning in the task of intrusion detection based on the analysis of industrial process state and ICS networking

Sokolov¹,

Pyatnitsky²,

Alabugin³

2019

FME Transactions

View full text Add to dashboard Cite

Modern industrial control systems (ICS) are increasingly becoming targets of cyber attacks. Traditional security tools based on a signature approach are not always able to detect a new attack, the signature of which has not yet been described. In particular, this occurs during targeted attacks on industrial facilities. Cyber attacks can cause anomalies in the operation of an industrial control system and process equipment under its control. Therefore, to detect attacks, it is advisable to use an approach based on the detection of anomalies. A reasonable way to implement this approach is to use machine learning techniques. The paper deals with the most common methods of machine learning (decision tree algorithms, linear algorithms, support vector machine) and neural networks. To assess their applicability in the problem of detection of ICS anomalies, the Additional Tennessee Eastman Process Simulation Data for Anomaly Detection Evaluation and Gas Pipeline datasets were used.

show abstract

Metaheuristic neural networks for anomaly recognition in industrial sensor networks with packet latency and jitter for smart infrastructures

Cited by 18 publications

References 44 publications

HML-IDS: A Hybrid-Multilevel Anomaly Prediction Approach for Intrusion Detection in SCADA Systems

HML-IDS: A Hybrid-Multilevel Anomaly Prediction Approach for Intrusion Detection in SCADA Systems

A Security Concept Based on Scaler Distribution of a Novel Intrusion Detection Device for Wireless Sensor Networks in a Smart Environment

Applying methods of machine learning in the task of intrusion detection based on the analysis of industrial process state and ICS networking

Contact Info

Product

Resources

About