Defending unknown attacks on cyber-physical systems by semi-supervised approach and available unlabeled data

Huda, Shamsul; Miah, Suruz; Hassan, Mohammad Mehedi; Islam, Rafiqul; Yearwood, John; Alrubaian, Majed; Almogren, Ahmad

doi:10.1016/j.ins.2016.09.041

Cited by 81 publications

(41 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Without a properly designed cyber-planning-physical system security, the whole system might be at risk of cyber-attacks such DDOS (Distributed Denial of Service), data theft, eavesdropping, and malicious software. The attacker can delete, modify, steal, or exploit the information and resources for inappropriate reasons [75]. Most published papers did not properly cover providing security involved with BIM.…”

Section: Cluster Securitymentioning

confidence: 99%

Industry 4.0 for the Construction Industry—How Ready Is the Industry?

et al. 2019

View full text Add to dashboard Cite

Technology and innovations have fueled the evolution of Industry 4.0, the fourth industrial revolution. Industry 4.0 encourages growth and development through its efficiency capacity, as documented in the literature. The growth of the construction industry is a subset of the universal set of the gross domestic product value; thus, Industry 4.0 has a spillover effect on the engineering and construction industry. In this study, we aimed to map the state of Industry 4.0 in the construction industry, to identify its key areas, and evaluate and interpret the available evidence. We focused our literature search on Web of Science and Scopus between January 2015 and May 2019. The search was dependent on the following keywords: “Industry 4.0” OR “Industrial revolution 4.0” AND TOPIC: “construction” OR “building”. From the 82 papers found, 20 full-length papers were included in this review. Results from the targeted papers were split into three clusters: technology, security, and management. With building information modelling (BIM) as the core in the cyber-physical system, the cyber-planning-physical system is able to accommodate BIM functionalities to improve construction lifecycle. This collaboration and autonomous synchronization system are able to automate the design and construction processes, and improve the ability of handling substantial amounts of heterogeneity-laden data. Industry 4.0 is expected to augment both the quality and productivity of construction and attract domestic and foreign investors.

show abstract

Section: Cluster Securitymentioning

confidence: 99%

Industry 4.0 for the Construction Industry—How Ready Is the Industry?

et al. 2019

View full text Add to dashboard Cite

show abstract

“…Additionally, high-dimensional auxiliary variables in chemical processes result in highly complex models and often incomplete model structures [56]. The moving window method can obtain the latest data representing the current process [57] and adaptively update that data [58], and the cosine similarity correlation calculation method can effectively measure the correlations between vectors [59] and identify the effectiveness of the influences [60]. Therefore, a sample data updating method using moving window--cosine similarity-based soft sensor modeling is proposed to update the sample datasets of soft sensor models for chemical processes and improve their prediction performance.…”

Section: Adaptive Soft Sensor Developmentmentioning

confidence: 99%

An adaptive soft sensor deterioration evaluation and model updating method for time-varying chemical processes

Dai

2020

CI&CEQ

View full text Add to dashboard Cite

Article Highlights • An adaptive soft sensor model deterioration evaluation method is proposed • An adaptive modeling sample data updating method is proposed • The RMSE and MAE of the fitting performance of the proposed method in a CSTR are improved • The RMSE and MAE of the predicted performances of the proposed method in a CSTR have lower values • The RMSE and MAE of the predicted performances of the proposed method in a DCP are the lowest average values

show abstract

“…Apart from Beehive, the proposed semi-supervised approach only by using K-Means approach can self-merge the information of unknown malware which is unlabeled data into detection system as discussed by [7]. The semi-supervised approach extracts the information of the cluster before inserts the information into the SVM, which is support vector machine classification system by applying global K-Means clustering algorithm.…”

Section: ) Identifying the Number Of Clusters (K)mentioning

confidence: 99%

Clustering Analysis for Malware Behavior Detection using Registry Data

Rosli¹,

Yassin²,

M.A³

et al. 2019

IJACSA

View full text Add to dashboard Cite

The increase of malware attacks may increase risk in information technology industry such as Industrial Revolution 4.0 that consists of multiple sectors especially in cyber security. Because of that malware detection technique plays vital role in detecting malware attack that can give high impact towards the cyber world. In accordance with the technique, one of unsupervised machine learning able to detect malware attack by identifying the behavior of the malware; which called clustering technique. Owing to this matter, current research shows a paucity of analysis in detecting malware behavior and limited source that can be used in identifying malware attacks. Thus, this paper introduce clustering detection model by using K-Means clustering approach to detect malware behavior of data registry based on the features of the malware. Clustering techniques that use unsupervised algorithm in machine learning plays an important role in grouping similar malware characteristics by studying the behavior of the malware. Throughout the experiment, malware features were selected and extracted from computer registry data and eventually used in the proposed clustering detection model to be clustered as normal or suspicious behavior. The results of the experiment indicates that this proposed model is capable to cluster normal and suspicious data into two separate groups with high detection rate which is more than 90 percent accuracy. Ultimately, the main contribution based on the findings is the proposed framework can be used to cluster the data with the use of data registry to detect malware.

show abstract

Defending unknown attacks on cyber-physical systems by semi-supervised approach and available unlabeled data

Cited by 81 publications

References 24 publications

Industry 4.0 for the Construction Industry—How Ready Is the Industry?

Industry 4.0 for the Construction Industry—How Ready Is the Industry?

An adaptive soft sensor deterioration evaluation and model updating method for time-varying chemical processes

Clustering Analysis for Malware Behavior Detection using Registry Data

Contact Info

Product

Resources

About