Intrusion Detection in Wi-Fi Networks by Modular and Optimized Ensemble of Classifiers: An Extended Analysis

Granato, Giuseppe; Martino, Alessio; Baldini, Luca; Rizzi, Antonello

doi:10.1007/s42979-022-01191-0

Cited by 4 publications

(5 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As anticipated, many research works focused on single-frame analysis [1,2,10,14,20], mainly highlighting that a subset of attacks can be effectively identified on a per-frame basis. As instead, in this work, we perform a study of the anomaly detection problem in WiFi networks expressed in the graph domain.…”

Section: Buffering and Graphs Building Proceduresmentioning

confidence: 97%

“…Furthermore, for the purpose of this work, numerical features are assumed to be normalized in [0, 1]. To perform processing on patterns (i.e., packets) defined in the starting features space, we adopt the following dissimilarity measure (already proposed in [1,2,20]) ad-hoc tailored to this heterogeneous structure. Let x and y be two generic patterns, then:…”

Section: Dissimilarity Measurementioning

confidence: 99%

“…• δ ∈ [0, 0.8] is the dropout rate for the neural network; • α ∈ [0.001, 0.05] is the parameter to setup the ADAM optimizer learning rate; • p ∈ [2,20] is the patience delta rate; • n (l) ∈ {1, . .…”

Section: Trainingmentioning

confidence: 99%

See 2 more Smart Citations

Graph-Based Multi-Label Classification for WiFi Network Traffic Analysis

et al. 2022

Self Cite

View full text Add to dashboard Cite

Network traffic analysis, and specifically anomaly and attack detection, call for sophisticated tools relying on a large number of features. Mathematical modeling is extremely difficult, given the ample variety of traffic patterns and the subtle and varied ways that malicious activity can be carried out in a network. We address this problem by exploiting data-driven modeling and computational intelligence techniques. Sequences of packets captured on the communication medium are considered, along with multi-label metadata. Graph-based modeling of the data are introduced, thus resorting to the powerful GRALG approach based on feature information granulation, identification of a representative alphabet, embedding and genetic optimization. The obtained classifier is evaluated both under accuracy and complexity for two different supervised problems and compared with state-of-the-art algorithms. We show that the proposed preprocessing strategy is able to describe higher level relations between data instances in the input domain, thus allowing the algorithms to suitably reconstruct the structure of the input domain itself. Furthermore, the considered Granular Computing approach is able to extract knowledge on multiple semantic levels, thus effectively describing anomalies as subgraphs-based symbols of the whole network graph, in a specific time interval. Interesting performances can thus be achieved in identifying network traffic patterns, in spite of the complexity of the considered traffic classes.

show abstract

Section: Buffering and Graphs Building Proceduresmentioning

confidence: 97%

Section: Dissimilarity Measurementioning

confidence: 99%

See 1 more Smart Citation

Graph-Based Multi-Label Classification for WiFi Network Traffic Analysis

et al. 2022

Self Cite

View full text Add to dashboard Cite

show abstract

“…These devices are used in various applications, such as healthcare, smart homes, and transportation [2]. However, they can be vulnerable to cyberattacks, such as data breaches, unauthorized access, and data manipulations [3]. To identify and prevent such attacks on IoT devices, a reliable and efficient IDS method is required [4].…”

Section: Introductionmentioning

confidence: 99%

MAC Protocol Based IoT Network Intrusion Detection Using Improved Efficient Shuffle Bidirectional COOT Channel Attention Network

Nayak

Bhattacharyya

2023

IEEE Access

View full text Add to dashboard Cite

The IoT networks are customized to work under various smart environments, utilizing diverse sensors. However, they are vulnerable to several cyberattacks because of their finite resources and limited computing capabilities. Intruders can easily hack the data transmitted across the end nodes. Therefore, it is crucial to protect the privacy of the IoT network against adversarial attacks. For real-time insights from IoT networks, an appropriate networking protocol is essential. In previous studies, several routing protocols have been formulated for intrusion detection with limited performance. Even the application of advanced machine learning (ML) has shown relatively lower accuracy with an increased error rate. To address these issues, an innovative intrusion detection system (IDS) for IoT networks based on medium access control (MAC) protocols with an improved efficient shuffle bidirectional COOT channel attention network (IEsBCCA-Net) method has been proposed. The suggested system uses the MAC protocol to securely transmit the data with low energy consumption and delay, which provides increased throughput. The collected data is stored in the BoT-IoT dataset, which is imbalanced and balanced using the synthetic minority over-sampling technique (SMOTE) and random under-sampling (RUS) techniques. The data is pre-processed using the reformed histogram equalization method, and the optimal features are selected using the modified honey badger algorithm (MHBA). Finally, the intrusions are classified using the IEsBCCA-Net approach, which provides outstanding accuracy compared to state-of-the-art (SOTA) methods. INDEX TERMSImproved efficient shuffle bidirectional COOT channel attention network, intrusion detection, IoT network, MAC protocol, modified honey badger algorithm. NANAVATH KIRAN SINGH NAYAK was born in Hyderabad, Telangana, India. He received the B.Tech. and M.Tech. degrees in electronics and communication engineering from Jawaharlal

show abstract

“…Moreover, in many real-world problems dealing with complex systems, the starting space is not a vectorial space, being also often non-metric ( e.g ., in life sciences ( Münch et al, 2020 ; Martino, Giuliani & Rizzi, 2018 ), engineering applications ( D’urso & Massari, 2019 ; De Santis, Arnò & Rizzi, 2022 ; Kim, Lee & Kim, 2018 ) or cybersecurity ( Granato et al, 2020 , 2022 )). Consequently, only the dissimilarity representation is available through the dissimilarity matrix, as stated above.…”

Section: Introductionmentioning

confidence: 99%

On component-wise dissimilarity measures and metric properties in pattern recognition

Santis

Martino

Rizzi

2022

PeerJ Computer Science

Self Cite

View full text Add to dashboard Cite

In many real-world applications concerning pattern recognition techniques, it is of utmost importance the automatic learning of the most appropriate dissimilarity measure to be used in object comparison. Real-world objects are often complex entities and need a specific representation grounded on a composition of different heterogeneous features, leading to a non-metric starting space where Machine Learning algorithms operate. However, in the so-called unconventional spaces a family of dissimilarity measures can be still exploited, that is, the set of component-wise dissimilarity measures, in which each component is treated with a specific sub-dissimilarity that depends on the nature of the data at hand. These dissimilarities are likely to be non-Euclidean, hence the underlying dissimilarity matrix is not isometrically embeddable in a standard Euclidean space because it may not be structurally rich enough. On the other hand, in many metric learning problems, a component-wise dissimilarity measure can be defined as a weighted linear convex combination and weights can be suitably learned. This article, after introducing some hints on the relation between distances and the metric learning paradigm, provides a discussion along with some experiments on how weights, intended as mathematical operators, interact with the Euclidean behavior of dissimilarity matrices.

show abstract

Intrusion Detection in Wi-Fi Networks by Modular and Optimized Ensemble of Classifiers: An Extended Analysis

Cited by 4 publications

References 50 publications

Graph-Based Multi-Label Classification for WiFi Network Traffic Analysis

Graph-Based Multi-Label Classification for WiFi Network Traffic Analysis

MAC Protocol Based IoT Network Intrusion Detection Using Improved Efficient Shuffle Bidirectional COOT Channel Attention Network

On component-wise dissimilarity measures and metric properties in pattern recognition

Contact Info

Product

Resources

About