DReAM: Deep Recursive Attentive Model for Anomaly Detection in Kernel Events

Ezeme, Okwudili M.; Mahmoud, Qusay H.; Azim, Akramul

doi:10.1109/access.2019.2897122

Cited by 18 publications

(14 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In recent years, studies using logs as an anomaly detection data source have received more and more attention [9]- [12]. The earliest log anomaly detection methods were mostly manual operations and rule-based methods [13].…”

Section: Introductionmentioning

confidence: 99%

nLSALog: An Anomaly Detection Framework for Log Sequence in Security Management

Yang

Gao

et al. 2019

IEEE Access

View full text Add to dashboard Cite

For the security defense in the current Intelligent Transportation System (ITS), malware is often used as the security analysis data source, but only the known attack type can be detected. A general anomaly detection framework is proposed, using log data as the analysis data source. By modeling the log template sequence as a natural language sequence and using the stacked Long Short-Term Memory (LSTM) with self-attention mechanism, the framework can effectively extract the hidden pattern of the log template sequence, and well express the dependencies inside the log template sequence. The experimental results show that the overall accuracy of log sequence anomaly detection of the detection framework is better than that of existing methods and the time cost is lower.

show abstract

Section: Introductionmentioning

confidence: 99%

nLSALog: An Anomaly Detection Framework for Log Sequence in Security Management

Yang

Gao

et al. 2019

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Still, they do not consider the temporal relationship amongst the sequence of the system calls. Also, in [17], [18], the hierarchical LSTM network is used to explore the understanding of relationships amongst the kernel event traces of an embedded system, but other features that ordinarily should yield a more representative model like timestamps, CPU cycles, and system call arguments are skipped.…”

Section: Related Workmentioning

confidence: 99%

Design and Development of AD-CGAN: Conditional Generative Adversarial Networks for Anomaly Detection

2020

Self Cite

View full text Add to dashboard Cite

Whether in the realm of software or hardware, datasets representing the state of systems are mostly imbalanced. This imbalance is because these systems' reliability requirements make the occurrence of an anomaly a rare phenomenon. Hence, most datasets on anomaly detection have a relatively small percentage that captures the anomaly. Recently, generative adversarial networks (GAN) have shown promising results in image generation tasks. Therefore, in this research work, we build on conditional GANs (CGAN) to generate plausible distributions of a given profile to solve the challenge of data imbalance in anomaly detection tasks and present a novel framework for anomaly detection. Firstly, we learn the pattern of the minority class data samples using a single class CGAN. Secondly, we use the knowledge base of the single class CGAN to generate samples that augment the minority class samples so that a binary class CGAN can train on the typical and malicious profiles with a balanced dataset. This approach inherently eliminates the bias imposed on algorithms from the dataset and results in a robust framework with improved generalization. Thirdly, the binary class CGAN generates a knowledge base that we use to construct the cluster-based anomaly detector. During testing, we do not use the single class CGAN, thereby providing us with a lean and efficient algorithm for anomaly detection that can do anomaly detection on semisupervised and non-parametric multivariate data. We test the framework on logs and image-based anomaly detection datasets with class imbalance. We compare the performance of AD-CGAN with GAN-derived and non-GAN-derived state of the art algorithms on benchmark datasets. AD-CGAN outperforms most of the algorithms in the standard metrics of Precision, Recall, and F-1 Score. Where AD-CGAN does not perform better in the parameters used, it has the advantage of being lightweight. Therefore, it can be deployed for both online and offline anomaly detection tasks since it does not use an input sample inversion strategy.

show abstract

“…Through the relationship between “generation and restraint,” the whole system of heaven and earth presents a relatively stable dynamic balance. Similarly, the relationship between formal control, social control, technology platform and ambidextrous learning of engineering project team can also show relatively stable dynamic balance through the relationship between “generation” and “restraint.” 7,8…”

Section: Introductionmentioning

confidence: 99%

“…Similarly, the relationship between formal control, social control, technology platform and ambidextrous learning of engineering project team can also show relatively stable dynamic balance through the relationship between "generation" and "restraint." 7,8 To sum up, this paper will build a theoretical framework between technical platforms (BIM, AI, VR, AR, MR), formal control, social control and ambidextrous learning of engineering project teams, and analyze it in combination with the five elements theory in traditional Chinese culture, collect data from the construction industry for hypothesis testing, and put forward management suggestions according to the research findings.…”

Section: Introductionmentioning

confidence: 99%

Ambidextrous learning of engineering project team: Relying on control or BIM AI VR AR MR?

Yang

Cui

2020

International Journal of Engineering Business Management

View full text Add to dashboard Cite

Through formal control and social control, technology platforms can acquire the information knowledge needed for ambidextrous learning of engineering project team, but whether technology platforms influence ambidextrous learning of engineering project team through the intermediary role of ambidextrous control (formal control, social control) is still lack of theoretical and empirical support. In order to explore the influence of the co-use of technology platform and ambidextrous control on the ambidextrous learning of engineering project team, this paper constructs a theoretical framework between the performance of ambidextrous control (formal control, social control) and different types of technology platform (BIM, AI, VR, AR, MR) and different types of learning (exploratory learning, exploitative learning). A questionnaire survey was conducted among 210 project managers. AMOS22.0 and bootstrap software were used for analysis and test, SPSS22.0 was used for hierarchical regression analysis, the results of hierarchical regression analysis show that formal control, social control and the balanced use of both have significant positive correlation with the ambidextrous learning and balanced use of ambidextrous learning of engineering project team. Formal Information Technology Platform (BIM) and Informal Information Technology Platform (AI, VR, AR, MR) have significant positive effects on the ambidextrous learning of engineering project team. The balanced use of formal Information Technology Platform (BIM) and informal Information Technology Platform (AI, AR) has significant positive effects on the ambidextrous learning balance of engineering project team. Formal control and social control mediate the positive correlation between information technology platform (BIM, AI, VR, AR, MR) and ambidextrous learning of engineering project team. In addition, information technology platform (BIM, AI, VR) regulates the impact of formal control and social control on learning (exploratory learning, exploitative learning). Generally speaking, different types of technology platforms and ambidextrous control strategies are still effective for the ambidextrous learning and balance of engineering project team.

show abstract

DReAM: Deep Recursive Attentive Model for Anomaly Detection in Kernel Events

Cited by 18 publications

References 23 publications

nLSALog: An Anomaly Detection Framework for Log Sequence in Security Management

nLSALog: An Anomaly Detection Framework for Log Sequence in Security Management

Design and Development of AD-CGAN: Conditional Generative Adversarial Networks for Anomaly Detection

Ambidextrous learning of engineering project team: Relying on control or BIM AI VR AR MR?

Contact Info

Product

Resources

About