Intrusion detection in cyber-physical systems using a generic and domain specific deep autoencoder model

Thakur, Soumyadeep; Chakraborty, Anuran; De, Rajonya; Kumar, Neeraj; Sarkar, Ram

doi:10.1016/j.compeleceng.2021.107044

Cited by 47 publications

(22 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Followed by the GSAE and AE-RF models which attained slightly enhanced 𝑎𝑐𝑐𝑢 𝑦 values of 97.44% and 97.55%, respectively. Though the FURIA model resulted in For ensuring the enhanced performance of the SFSA-DLIDS model, a comparative examination is made in Table 4 [3,13]. The results implied that the WISARD, Forest-PA, and LIB-SVM models have obtained lower accu y values of 96.22%, 96.53%, and 96.56% respectively.…”

Section: Resultsmentioning

confidence: 98%

“…The experimental outcome shows the SFSA-DLIDS algorithm gained higher values of TA and VA. To be specific, the VA is higher than TA. For ensuring the enhanced performance of the SFSA-DLIDS model, a comparative examination is made in Table 4 [3,13]. The results implied that the WISARD, Forest-PA, and LIB-SVM models have obtained lower 𝑎𝑐𝑐𝑢 𝑦 values of 96.22%, 96.53%, and 96.56% respectively.…”

Section: Resultsmentioning

confidence: 99%

“…CPS is a multi-dimensional, complex system that integrates a computer, network, and physical environment [2]. With the deep collaboration of 3C (control, computation, and communication) techniques, the dynamic control, information servicing, and real-time perception of large engineering systems are realized [3]. CPS realizes the organic design of physical, computation, and transmission systems, making the system capable, reliable, and effective for simultaneous collaboration, resulting in extensive and important application prospects.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Evolutionary-Based Deep Stacked Autoencoder for Intrusion Detection in a Cloud-Based Cyber-Physical System

et al. 2022

View full text Add to dashboard Cite

As cyberattacks develop in volume and complexity, machine learning (ML) was extremely implemented for managing several cybersecurity attacks and malicious performance. The cyber-physical systems (CPSs) combined the calculation with physical procedures. An embedded computer and network monitor and control the physical procedure, commonly with feedback loops whereas physical procedures affect calculations and conversely, at the same time, ML approaches were vulnerable to data pollution attacks. Improving network security and attaining robustness of ML determined network schemes were the critical problems of the growth of CPS. This study develops a new Stochastic Fractal Search Algorithm with Deep Learning Driven Intrusion Detection system (SFSA-DLIDS) for a cloud-based CPS environment. The presented SFSA-DLIDS technique majorly focuses on the recognition and classification of intrusions for accomplishing security from the CPS environment. The presented SFSA-DLIDS approach primarily performs a min-max data normalization approach to convert the input data to a compatible format. In order to reduce a curse of dimensionality, the SFSA technique is applied to select a subset of features. Furthermore, chicken swarm optimization (CSO) with deep stacked auto encoder (DSAE) technique was utilized for the identification and classification of intrusions. The design of a CSO algorithm majorly focuses on the parameter optimization of the DSAE model and thereby enhances the classifier results. The experimental validation of the SFSA-DLIDS model is tested using a series of experiments. The experimental results depict the promising performance of the SFSA-DLIDS model over the recent models.

show abstract

Section: Resultsmentioning

confidence: 98%

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Evolutionary-Based Deep Stacked Autoencoder for Intrusion Detection in a Cloud-Based Cyber-Physical System

et al. 2022

View full text Add to dashboard Cite

show abstract

“…The technique employs pre‐processing of packets, merging data, and malicious data labeling. To sort out the effective detection rate, integration of feature‐selection algorithm and supervised‐learning technique is carried out 8 . ANN (artificial neural networks) platform based on a machine‐learning algorithm involving the wrapper‐feature selection methods overtakes the network data classification of SVM‐classifiers.…”

Section: Introductionmentioning

confidence: 99%

“…The significant feature points could be originated from imbalanced data, such it requires choosing out original data subset and subjects for the dataset resampling process. This resampling process facilitates evening‐out features, equally in a balanced class, and it yields better performance for classifying outcomes 8 …”

Section: Introductionmentioning

confidence: 99%

An efficient cyber‐physical system using hybridized enhanced support‐vector machine with Ada‐Boost classification algorithm

Sharma

Shandilya

2022

Concurrency and Computation

View full text Add to dashboard Cite

The necessity of cyber-security has obtained immense importance in day-to-day concerns of network communication. Therefore, several available research works predominantly focus on network security to protect the resources, services, and networks from any unauthorized access. A CPS (cyber-physical system) model using a dual mutation-based genetic algorithm, with feature classification through Ada-Boost and SVM classifier is proposed in this paper. Dual-mutation based genetic-algorithm overcomes the issues of conventional techniques including convergence issues and local fine-tuning of features. In this paper, necessary modifications were made to the existing Genetic Algorithm (GA) method to reduce the random nature of the traditional GA method. Particularly, the goal of this work is to develop the modified reproduction operators with appropriate fitness functions to guide simulations to gain optimal solutions. In floating-point representation, every chromosome vector has been coded as a floating-point number vector having the same length as the solution vector. Each element was selected initially, to stand within the desired domain, and operators were designed carefully in satisfying the constraints. As a result, there are various enhancements employed in the dual-mutation algorithm that handles local fine-tuned features.The relevant features of dataset samples are extracted and rescaled using feature selection and resampling phase aided by the Markov-resampling process. Followed by this, a hybrid approach of ESVM (enhanced support-vector machine) algorithm with Ada-Boost classifier is implemented for the fault classification process. The performance assessment was explicated in terms of accuracy-factor, F1-score, and execution time. Comparative analysis expounded the efficacy of the proposed model than other conventional methods attaining higher accuracy (97%), F1-score (99%) rates, and less execution time (15.33 s).

show abstract

Hybrid deep architecture for intrusion detection in cyber‐physical system: An optimization‐based approach

Arumugam,

Paul,

Issac

et al. 2024

Adaptive Control & Signal

View full text Add to dashboard Cite

SummaryIntrustion Detection System (IDS) refers to the gear or software that monitors a network or system for malicious activity or policy violations. Periodically, the system records any intrusion action or breach, which frequently modifies the administrator. Cyber Physical System (CPS) is particularly called as networked connected system, in which the system components are spatially distributed and integrated via the communication network. The control mechanism ensures computation significance; however, the system does affect attacks. Researchers are trying to handle this issue via the existing anomaly datasets. In this way, this paper follows an intrusion detection system under three major stages including extraction of features, selection of feature, and detection. The primary stage is the extraction of Statistical features like standard deviation, mean, mode, variance, and median, as well as higher‐order statistical features like moment, percentile, improved correlation, kurtosis, mutual information, skewness, flow‐based features, and information gain‐based features. The curse of dimensionality becomes a significant problem in this scenario, so it is crucial to choose the right features. Improved Linear Discriminant Analysis (LDA) is utilized to choose the right features. The selected features are subjected to a Hybrid classifier for final detection. Here, models like CNN (Convolutional Neural Network) and Bi‐GRU (Bidirectional Gated Recurrent Unit) are combined. A new Bernoulli Map Estimated Arithmetic Optimization Algorithm (BMEAOA) is added to train the system by adjusting the ideal weights of the two classifiers, leading to improved detection outcomes. Ultimately, the effectiveness is assessed in comparison to the other traditional techniques.

show abstract

Intrusion detection in cyber-physical systems using a generic and domain specific deep autoencoder model

Cited by 47 publications

References 18 publications

Evolutionary-Based Deep Stacked Autoencoder for Intrusion Detection in a Cloud-Based Cyber-Physical System

Evolutionary-Based Deep Stacked Autoencoder for Intrusion Detection in a Cloud-Based Cyber-Physical System

An efficient cyber‐physical system using hybridized enhanced support‐vector machine with Ada‐Boost classification algorithm

Hybrid deep architecture for intrusion detection in cyber‐physical system: An optimization‐based approach

Contact Info

Product

Resources

About