Machine Learning and Deep Learning framework with Feature Selection for Intrusion Detection

Lakshmanarao, A.; Srisaila, A.; Kiran, T. Srinivasa Ravi

doi:10.1109/ic3iot53935.2022.9767727

Cited by 4 publications

(1 citation statement)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Another method of security in big data is to create trust between the sender and the receiver. Many methods such as data mining [10], supervised [11] and unsupervised [12] machine learning algorithms have been used for the trust in data quality. Trust plays an important role in the security [12]- [14].…”

Section: Introductionmentioning

confidence: 99%

Reputation-based Security model for detecting biased attacks in BigData

Desai

Annappaiah

2023

IJEECS

View full text Add to dashboard Cite

As internet of things (IoT) devices are increasing since the emergence of these devices in 2010, the data stored by these devices should have a proper security measure so that it can be stored without getting in hands of an attacker. The data stored has to be analyzed whether the data is safe or malicious, as the malicious data can corrupt the whole information. The security model in BigData has many challenges such as vulnerability to fake data generation, troubles with cryptographic protection, and absent security audits. As cyberattacks are increasing the main objective of each organization is to secure the data efficiently. This paper presents a model of reputation security for the detection of biased attacks on BigData. The proposed model provides various evaluation models to identify biased attack in malicious IoT devices and provide a secure communication metric for BigData. The results show better rates in terms of attack detection rate, attack detection failure rata, system throughput and number of dead nodes when the attack rate is increased when compared with the existing reputation-based security (ERS) model. Moreover, this model reputation-based biased attack detection (RBAD) increases the security of the IoT devices in the BigData and reduces the biased attack coming from various malicious nodes.

show abstract

Section: Introductionmentioning

confidence: 99%

Reputation-based Security model for detecting biased attacks in BigData

Desai

Annappaiah

2023

IJEECS

View full text Add to dashboard Cite

show abstract

Attention features selection oversampling technique (AFS-O) for rolling bearing fault diagnosis with class imbalance

Han,

Wang,

Shen

et al. 2023

Meas. Sci. Technol.

View full text Add to dashboard Cite

When using data-driven methods for fault diagnosis of mechanical rotating components such as gears and bearings, there is a problem of class imbalance in the lifecycle data collected by sensors. The most commonly used method to address this issue is the synthetic minority over-sampling technique, which synthesizes samples in the feature space, but its blind synthesis may lead to redundant features in the synthetic samples. To avoid this deficiency, this paper proposes a feature-weighted oversampling method called AFS-O (Attention Features Selection Oversampling Technique). First, time–frequency domain features are extracted from the full lifecycle data of bearings to construct an initial subset of features, which serves the input to AFS. Then, AFS is then used to obtain the distribution of feature selection patterns and generate feature weights to determine the inclusion or exclusion of each feature, thereby constructing an optimal subset of features. Finally, the optimal feature subset is synthetically oversampled to achieve class-balanced data, which is then fed into a classifier. AFS-O is applied to the rolling bearing accelerated lifetime dataset from Xi’an Jiaotong University. Experimental results demonstrate that AFS-O outperforms other state-of-the-art synthetic oversampling algorithms in terms of Gmean, F 2 score , and Recall, confirming the effectiveness of the proposed method.

show abstract