A Cyber Intrusion Detection Method based on Focal Loss Neural Network

Cheng, Zhonghao; Chai, Senchun

doi:10.23919/ccc50068.2020.9189108

Cited by 11 publications

(6 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The adeptness of FL has been applied and tested for object detection, computer vision in an imbalanced dataset, and attained incredible performance [ 48 ]. However, the usefulness of FL is not restricted to only computer vision; it is also applied to intrusion detection for imbalanced data issues [ 46 ].…”

Section: Materials and Methodsmentioning

confidence: 99%

“…The cost matrix can be customized for better learning of misclassified samples using cost-sensitive learning. The represented cost matrix is used to reduce the probability of misclassification by many researchers [ 44 , 45 , 46 , 47 ].…”

Section: Introductionmentioning

confidence: 99%

“…As a result, the VAE can generate minority class samples as close to the original input, which will, in turn, lead to better performance of intrusion classifier and reduce FPR, increase the detection performance of minority and low-frequency attacks. It is worth mentioning that the FL was implemented in intrusion detection very recently [ 46 , 47 ]. Additionally, several studies demonstrated that the FL improved the performance of deep learning algorithms in the field of computer vision and IoT applications [ 48 , 49 , 50 , 51 ].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Towards an Effective Intrusion Detection Model Using Focal Loss Variational Autoencoder for Internet of Things (IoT)

Khanam

Ahmedy

Idris

et al. 2022

Sensors

View full text Add to dashboard Cite

As the range of security attacks increases across diverse network applications, intrusion detection systems are of central interest. Such detection systems are more crucial for the Internet of Things (IoT) due to the voluminous and sensitive data it produces. However, the real-world network produces imbalanced traffic including different and unknown attack types. Due to this imbalanced nature of network traffic, the traditional learning-based detection techniques suffer from lower overall detection performance, higher false-positive rate, and lower minority-class attack detection rates. To address the issue, we propose a novel deep generative-based model called Class-wise Focal Loss Variational AutoEncoder (CFLVAE) which overcomes the data imbalance problem by generating new samples for minority attack classes. Furthermore, we design an effective and cost-sensitive objective function called Class-wise Focal Loss (CFL) to train the traditional Variational AutoEncoder (VAE). The CFL objective function focuses on different minority class samples and scrutinizes high-level feature representation of observed data. This leads the VAE to generate more realistic, diverse, and quality intrusion data to create a well-balanced intrusion dataset. The balanced dataset results in improving the intrusion detection accuracy of learning-based classifiers. Therefore, a Deep Neural Network (DNN) classifier with a unique architecture is then trained using the balanced intrusion dataset to enhance the detection performance. Moreover, we utilize a challenging and highly imbalanced intrusion dataset called NSL-KDD to conduct an extensive experiment with the proposed model. The results demonstrate that the proposed CFLVAE with DNN (CFLVAE-DNN) model obtains promising performance in generating realistic new intrusion data samples and achieves superior intrusion detection performance. Additionally, the proposed CFLVAE-DNN model outperforms several state-of-the-art data generation and traditional intrusion detection methods. Specifically, the CFLVAE-DNN achieves 88.08% overall intrusion detection accuracy and 3.77% false positive rate. More significantly, it obtains the highest low-frequency attack detection rates for U2R (79.25%) and R2L (67.5%) against all the state-of-the-art algorithms.

show abstract

Section: Materials and Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Towards an Effective Intrusion Detection Model Using Focal Loss Variational Autoencoder for Internet of Things (IoT)

Khanam

Ahmedy

Idris

et al. 2022

Sensors

View full text Add to dashboard Cite

show abstract

“…A working principle of an artificial neural network (ANN) is based on supervised learning from the system's previous experiences using labelled data as a training set. The system's performance is influenced by a number of factors such as training function, magnitude of the data, capability of the computer, and so on [6]. Xiang et al proposed a hierarchy-based hybrid method.…”

Section: Related Workmentioning

confidence: 99%

“…Expert systems, intelligent controls, neural networks, and natural language processing are just a few examples of how AI staff can apply their methods to every field of human intellectual activity. For difficulties that humans face in a variety of domains, AI technology gives excellent answers in a minimal number of steps [4][5][6][7]. It primarily consists of state graph search tools, predicate logic reasoning techniques, and organized problem-solving approaches based on state graphs, reasoning techniques based on predicate logic, and solving techniques based on organized knowledge representation, such as semantic and ESnetworks, are a few examples [8][9][10][11][12].…”

Section: Introductionmentioning

confidence: 99%

Artificial Intelligence Based System for Securing Computer Networks: A Survey

Singh

Kumar

Reddy

et al. 2023

Advances in Transdisciplinary Engineering

View full text Add to dashboard Cite

The security of computer networks is crucial in today’s computer systems. A number of software technologies are now being developed in order to impose high levels of protection against harmful attacks. Because of their potential to detect and prevent assaults by malicious network users, intrusion detection systems have recently become a hot research issue. This article discusses various recent techniques such as anomaly, signature, open source IDS such as SNORT, machine learning, and edge assisted technologies in detail, along with the advantages and disadvantages of the deployed system. The tools used, datasets, performance metrics, and the accuracy of the methodologies are compared, and it gives a clear view of further advancements in computer networks. Based on the studies, it can be said that machine learning algorithms work better than other traditional methods and make security better.

show abstract