Improving threat detection in networks using deep learning

Schuartz, Fábio César; Fonseca, Mauro; Munaretto, Anelise

doi:10.1007/s12243-019-00743-5

Cited by 7 publications

(4 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…By using DL techniques, we can model a prediction system that is effective and adaptive in exploring and classifying volatile and unpredicted intrusions, which are inherent in dynamic attack techniques. A large portion of the study is lacking in the examination of features' misperception related aspects during learning, as well as in the assessment of false-positive (FP) and false-negative (FN) rates during prediction [7,8,21,25].…”

Section: Figure 1: Proposed Ids Framework Environmentmentioning

confidence: 99%

IoT Based Intrusion Detection System for Healthcare Using RNNBiLSTM Deep Learning Strategy with Custom Features

Jeyanthi¹,

Indrani

2022

Preprint

View full text Add to dashboard Cite

Internet of Things (IoT) devices exchange information directly between devices. They are more prone to vulnerability because of the design of the network layer in its architecture and also connected to the internet 24X7. IoT-based smart healthcare devices like patient monitoring cameras in hospital create life-saving data that must be shielded from intruders. Effective intrusion detection is required to safeguard sensitive private data before assault takes place due to the humongous data created by the IoT. This work proposes a 5-layered framework to find intrusion in large datasets. This work uses constructing new custom features to increase the learning rate and to reduce imperceptions during learning by the machine model. The proposed ACAAS algorithm obtains significant features and Recurrent Neural Networks with Long Short-Term Memory in both directions (RNNBiLSTM) is used to identify the assault to optimize the prediction performance accuracy by using the IoTID20 dataset to protect IoT networks. The experiment results provided Accuracy Rate of 99.16%, Error Rate of 0.008371%, Sensitivity Ratio of 99.89% and Specificity Ratio of 98.203% for IoTID20 with custom features using RNNBiLSTM. The obtained high accuracy rate shows the effectiveness of the system in protecting the network from intruders.

show abstract

Section: Figure 1: Proposed Ids Framework Environmentmentioning

confidence: 99%

IoT Based Intrusion Detection System for Healthcare Using RNNBiLSTM Deep Learning Strategy with Custom Features

Jeyanthi¹,

Indrani

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Unfortunately, KDD-99 has numerous flaws that make it unsuitable for current applications, including its age, excessively skewed goals, inconstant across training and test data sets, pattern duplication and irrelevant features. Tavallaee et al (2009) proposed NSL-KDD, a more balanced resampling of KDD-99 (Saba, 2020; Begli et al , 2019; Alrawashdeh and Purdy, 2016; Lin et al , 2018; Yang et al , 2019; Schuartz et al , 2020) have considered the KDD-Cup99 data set to demonstrate machine learning and deep learning algorithms to evaluate the proposed method performance, as mentioned in Table 1. But both data set lacks contemporary cyber-attack samples and is considered outdated and does not include recent IoT botnet attack samples.…”

Section: Literature Surveymentioning

confidence: 99%

“…The results are evaluated, analyzed and their effects are discussed. (Saba, 2020;Begli et al, 2019;Alrawashdeh and Purdy, 2016;Lin et al, 2018;Yang et al, 2019;Schuartz et al, 2020) have considered the KDD-Cup99 data set to demonstrate machine learning and deep learning algorithms to evaluate the proposed method performance, as mentioned in Table 1. But both data set lacks contemporary cyber-attack samples and is considered outdated and does not include recent IoT botnet attack samples.…”

Section: Introductionmentioning

confidence: 99%

Network traffic analysis through deep learning for detection of an army of bots in health IoT network

Geetha

S.H.

2022

IJPCC

View full text Add to dashboard Cite

Purpose IoT has a wide range of applications in the health-care sector and has captured the interest of many academic and industrial communities. The health IoT devices suffer from botnet attacks as all the devices are connected to the internet. An army of compromised bots may form to launch a DDoS attack, steal confidential data of patients and disrupt the service, and hence detecting this army of bots is paramount. This study aims to detect botnet attacks in health IoT devices using the deep learning technique. Design/methodology/approach This paper focuses on designing a method to protect health IoT devices from botnet attacks by constantly observing communication network traffic and classifying them as benign and malicious flow. The proposed algorithm analyzes the health IoT network traffic through implementing Bidirectional long-short term memory, a deep learning technique. The IoT-23 data set is considered for this research as it includes diverse botnet attack scenarios. Findings The performance of the proposed method is evaluated using attack prediction accuracy. It results in the highest accuracy of 84.8%, classifying benign and malicious traffic. Originality/value The proposed method constantly monitors the health IoT network to detect botnet attacks and classifies the traffic as benign or attack. The system is implemented using the BiLSTM algorithm and trained using the IoT-23 data set. The diversity of attack scenarios of the IoT-23 data set demonstrates the proposed algorithm's competence in detecting botnet types in a heterogeneous environment.

show abstract

“…In 2020 Schwartz F. et al [97] focused on dimension reduction to reduce complicated and reducing time for building model. An autoencoder (AE) is a deep neural network used to reduce the big data with, Autoencoder (SAE) for feature extraction to reduce the feature space.…”

Section: Auto-encoder (Ae)mentioning

confidence: 99%

Deep Learning Approaches for Intrusion Detection

Salih

Ameen

Zeebaree

et al. 2021

AJRCoS

View full text Add to dashboard Cite

Recently, computer networks faced a big challenge, which is that various malicious attacks are growing daily. Intrusion detection is one of the leading research problems in network and computer security. This paper investigates and presents Deep Learning (DL) techniques for improving the Intrusion Detection System (IDS). Moreover, it provides a detailed comparison with evaluating performance, deep learning algorithms for detecting attacks, feature learning, and datasets used to identify the advantages of employing in enhancing network intrusion detection.

show abstract

Improving threat detection in networks using deep learning

Cited by 7 publications

References 23 publications

IoT Based Intrusion Detection System for Healthcare Using RNNBiLSTM Deep Learning Strategy with Custom Features

IoT Based Intrusion Detection System for Healthcare Using RNNBiLSTM Deep Learning Strategy with Custom Features

Network traffic analysis through deep learning for detection of an army of bots in health IoT network

Deep Learning Approaches for Intrusion Detection

Contact Info

Product

Resources

About