Fast kNN Classifiers for Network Intrusion Detection System

Rao, B. Basaveswara; Swathi, K.

doi:10.17485/ijst/2017/v10i14/93690

Cited by 27 publications

(13 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The authors of [17,18] use the KNN method as a basis for their cybersecurity methods. In [17], Bilge et al use Indexed Partial Distance Search k-Nearest Neighbor (IKPDS) to test different types of attacks, and it results in an accuracy of 99.6%. Shapoorifard and Shamsinejad in [18] focus on reducing the false alarm rate and show an accuracy of 85.2% [18].…”

Section: Related Workmentioning

confidence: 99%

Intrusion Detection System for Healthcare Systems Using Medical and Network Data: A Comparison Study

et al. 2020

View full text Add to dashboard Cite

Introducing IoT systems to healthcare applications has made it possible to remotely monitor patients' information and provide proper diagnostics whenever needed. However, providing high-security features that guarantee the correctness and confidentiality of patients' data is a significant challenge. Any alteration to the data could affect the patients' treatment, leading to human casualties in emergency conditions. Due to the high dimensionality and prominent dynamicity of the data involved in such systems, machine learning has the promise to provide an effective solution when it comes to intrusion detection. However, most of the available healthcare intrusion detection systems either use network flow metrics or patients' biometric data to build their datasets. This paper aims to show that combining both network and biometric metrics as features performs better than using only one of the two types of features. We have built a real-time Enhanced Healthcare Monitoring System (EHMS) testbed that monitors the patients' biometrics and collects network flow metrics. The monitored data is sent to a remote server for further diagnostic and treatment decisions. Man-in-the-middle cyber-attacks have been used, and a dataset of more than 16 thousand records of normal and attack healthcare data has been created. The system then applies different machine learning methods for training and testing the dataset against these attacks. Results prove that the performance has improved by 7% to 25% in some cases, and this shows the robustness of the proposed system in providing proper intrusion detection.

show abstract

Section: Related Workmentioning

confidence: 99%

Intrusion Detection System for Healthcare Systems Using Medical and Network Data: A Comparison Study

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Tharwat et al (2013), the authors designed and developed three different classifiers based on KNN classifier's concept for facial age estimation to achieve high efficiency. Rao and Swathi (2017) adapted two fast KNN classification algorithms i.e., Indexed Partial Distance Search k-Nearest Neighbor (IKPDS), Partial Distance Search k-Nearest Neighbor (KPDS) and comparing with traditional KNN classification for Network Intrusion Detection on NSL-KDD dataset 2017 (NSL-KDD, 2009). Benaddi et al (2018), the authors propose to use PCA-fuzzy Clustering-KNN method which ensemble of Analysis of Principal Component and Fuzzy Clustering with K-Nearest Neighbor feature selection technics to detect anomalies.…”

Section: Machine Learning Models To Network Anomaly Detectionmentioning

confidence: 99%

Toward an Online DoS/DDoS Classification: An Empirical Study for Network Intrusion Detection Systems

Hai¹,

Khiem²,

Phúc³

2021

Journal of Computer Science

View full text Add to dashboard Cite

“…Experimented with a wide variety of attacks and different k values, Rao et al [8] used Indexed Partial Distance Search k-Nearest Neighbor (IKPDS) to recognize attacks. ey tested their method with 12,597 samples that were randomly selected from the NSL-KDD dataset, resulting in 99.6% accuracy in their experiment.…”

Section: Introductionmentioning

confidence: 99%

“…ST, T, x, N, l, α, where ST is the substitute model, T is the target model, x is the network flow data, N is the iteration steps, l is original label, and α is the move step Output: traffic adversarial example x adv (1) setx adv � x (2) for i ∈ [0, N − 1]do (3) loss L � cross entropy (l, ST(x adv )) (4) gradient G � ▽ x adv L (5) perturbation η � D • (αO(G)),where O(•) is shown in equation (8) (6) set x adv � x adv + η (7) if ST(x adv ) ≠ l and T(x adv ) ≠ l then(8) break (9) end if (10) if x adv � x then(11) break (12) end if (13) end for (14) return x adv ALGORITHM 2: Network flow adversarial example generate algorithm.…”

mentioning

confidence: 99%

A Black-Box Attack Method against Machine-Learning-Based Anomaly Network Flow Detection Models

Guo

Zhao

et al. 2021

Security and Communication Networks

View full text Add to dashboard Cite

In recent years, machine learning has made tremendous progress in the fields of computer vision, natural language processing, and cybersecurity; however, we cannot ignore that machine learning models are vulnerable to adversarial examples, with some minor malicious input modifications, while appearing unmodified to human observers, the outputs of machine learning-based model can be misled easily. Likewise, attackers can bypass machine-learning-based security defenses model to attack systems in real time by generating adversarial examples. In this paper, we propose a black-box attack method against machine-learning-based anomaly network flow detection algorithms. Our attack strategy consists in training another model to substitute for the target machine learning model. Based on the overall understanding of the substitute model and the migration of the adversarial examples, we use the substitute model to craft adversarial examples. The experiment has shown that our method can attack the target model effectively. We attack several kinds of network flow detection models, which are based on different kinds of machine learning methods, and we find that the adversarial examples crafted by our method can bypass the detection of the target model with high probability.

show abstract

Fast kNN Classifiers for Network Intrusion Detection System

Cited by 27 publications

References 6 publications

Intrusion Detection System for Healthcare Systems Using Medical and Network Data: A Comparison Study

Intrusion Detection System for Healthcare Systems Using Medical and Network Data: A Comparison Study

Toward an Online DoS/DDoS Classification: An Empirical Study for Network Intrusion Detection Systems

A Black-Box Attack Method against Machine-Learning-Based Anomaly Network Flow Detection Models

Contact Info

Product

Resources

About