Intelligent intrusion detection systems using artificial neural networks

Shenfield, Alex; Day, David; Ayesh, Aladdin

doi:10.1016/j.icte.2018.04.003

Cited by 204 publications

(78 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…There is a large body of work on using artificial (deep) neural networks for anomaly detection [29,30] and intrusion detection [31][32][33] that covers at least two decades of research. This previous research compared different approaches in terms of the best classification accuracy or recognition rates.…”

Section: Intrusion Detection With a (Deep) Neural Network-based Anomamentioning

confidence: 99%

Chained Anomaly Detection Models for Federated Learning: An Intrusion Detection Case Study

et al. 2018

View full text Add to dashboard Cite

The adoption of machine learning and deep learning is on the rise in the cybersecurity domain where these AI methods help strengthen traditional system monitoring and threat detection solutions. However, adversaries too are becoming more effective in concealing malicious behavior amongst large amounts of benign behavior data. To address the increasing time-to-detection of these stealthy attacks, interconnected and federated learning systems can improve the detection of malicious behavior by joining forces and pooling together monitoring data. The major challenge that we address in this work is that in a federated learning setup, an adversary has many more opportunities to poison one of the local machine learning models with malicious training samples, thereby influencing the outcome of the federated learning and evading detection. We present a solution where contributing parties in federated learning can be held accountable and have their model updates audited. We describe a permissioned blockchain-based federated learning method where incremental updates to an anomaly detection machine learning model are chained together on the distributed ledger. By integrating federated learning with blockchain technology, our solution supports the auditing of machine learning models without the necessity to centralize the training data. Experiments with a realistic intrusion detection use case and an autoencoder for anomaly detection illustrate that the increased complexity caused by blockchain technology has a limited performance impact on the federated learning, varying between 5 and 15%, while providing full transparency over the distributed training process of the neural network. Furthermore, our blockchain-based federated learning solution can be generalized and applied to more sophisticated neural network architectures and other use cases.

show abstract

Section: Intrusion Detection With a (Deep) Neural Network-based Anomamentioning

confidence: 99%

Chained Anomaly Detection Models for Federated Learning: An Intrusion Detection Case Study

et al. 2018

View full text Add to dashboard Cite

show abstract

“…It accepts one or more inputs and performs their weighted sum, which is then passed as an input to a non-linear function called as activation function. Example of IoT use-case that implemented ANN is intelligent intrusion detection [71].…”

Section: Machine Learning Techniquesmentioning

confidence: 99%

Data Analytics in the Internet of Things: A Survey

Saleem

Chishti

2019

SCPE

View full text Add to dashboard Cite

The plethora of sensors deployed in Internet of Things (IoT) environments generate unprecedented volumes of data, thereby creating a data deluge. Data collected from these sensors can be used to comprehend, examine and control intricate environments around us, facilitating greater intelligence, smarter decision-making, and better performance. The key challenge here is how to mine out proﬁcient information from such immense data. Copious solutions have been put forth to obtain valuable inferences and insights, however, these solutions are still in their developing stages. Moreover, conventional procedures do not address the surging analytical demands of IoT systems. Motivated to resolve this concern, this work investigates the key enablers for performing desired data analytics in IoT applications. A comprehensive survey on the identiﬁed key enablers including their role in IoT data analytics, use cases in which they have been applied and the corresponding IoT applications for the use cases is presented. Furthermore, open research challenges and future research opportunities are also discussed. This article can be used as a basis to foster advanced research in the arena of IoT data analytics.

show abstract

“…Alex et al [20] suggested that the IDS to analyze the data packets and to detect malicious shell code. In their work, integer values were obtained by converting the byte level data retrieved from the data transmission of the nodes and fed into the ANN.…”

Section: Related Workmentioning

confidence: 99%

ANNIDS: Artificial Neural Network based Intrusion Detection System for Internet of Things

Anitha*¹,

Arockiam²

2019

IJITEE

View full text Add to dashboard Cite

 Abstract: Internet of Things (IoT) makes everything in the real world to get connected. The resource constrained characteristics and the different types of technology and protocols tend to the IoT be more vulnerable than the conventional networks. Intrusion Detection System (IDS) is a tool which monitors analyzes and detects the abnormalities in the network activities. Machine Learning techniques are implemented with the Intrusion detection systems to enhance the performance of IDS. Various studies on IoT reveals that Artificial Neural Network (ANN) provides better accuracy and detection rate than other approaches. In this paper, an Artificial Neural Network based IDS (ANNIDS) technique based on Multilayer Perceptron (MLP) is proposed to detect the attacks initiated by the Destination Oriented Direct Acyclic Graph Information Solicitation (DIS) attack and Version attack in IoT environment. Contiki O.S/Cooja Simulator 3.0 is used for the IoT simulation.

show abstract

Intelligent intrusion detection systems using artificial neural networks

Cited by 204 publications

References 13 publications

Chained Anomaly Detection Models for Federated Learning: An Intrusion Detection Case Study

Chained Anomaly Detection Models for Federated Learning: An Intrusion Detection Case Study

Data Analytics in the Internet of Things: A Survey

ANNIDS: Artificial Neural Network based Intrusion Detection System for Internet of Things

Contact Info

Product

Resources

About