Non-linear Dimensionality Reduction-based Intrusion Detection using Deep Autoencoder
Journal Title: International Journal of Advanced Computer Science & Applications - Year 2019, Vol 10, Issue 8
Abstract
The intrusion detection has become core part of any network of computers due to increasing amount of digital content available. In parallel, the data breaches and malware attacks have also grown in large numbers which makes the role of intrusion detection more essential. Even though many existing techniques are successfully used for detecting intruders but new variants of malware and attacks are being released every day. To counterfeit these new types of attacks, intrusion detection must be designed with state of art techniques such as Deep learning. At present the Deep learning techniques have a strong role in Natural Language Processing, Computer Vision and Speech Processing. This paper is focused on reviewing the role of deep learning techniques for intrusion detection and proposing an efficient deep Auto Encoder (AE) based intrusion detection technique. The intrusion detection is implemented in two stages with a binary classifier and multiclass classification algorithm (dense neural network). The performance of the proposed approach is presented and compared with parallel methods used for intrusion detection. The reconstruction error of the AE model is compared with the PCA and the performance of both anomaly detection and the multiclass classification is analyzed using metrics such as accuracy and false alarm rate. The compressed representation of the AE model helps to lessen the false alarm rate of both anomaly detection and attack classification using SVM and dense NN model respectively.
Authors and Affiliations
S. Sreenivasa Chakravarthi, R. Jagadeesh Kannan
Keywords
Related Articles
- EP ID EP626602
- DOI 10.14569/IJACSA.2019.0100822
- Views 124
- Downloads 0
Multi Agent Architecture for Search Engine
The process of retrieving information is becoming ambiguous day by day due to huge collection of documents present on web. A single keyword produces millions of results related to given query but these results are not up...
An Effective Approach to Analyze Algorithms with Linear O(n) Worst-Case Asymptotic Complexity
A theoretical approach of asymptote analyzes the algorithms for approximate time complexity. The worst-case asymptotic complexity classifies an algorithm to a certain class. The asymptotic complexity for algorithms retur...
Cloud Security based on the Homomorphic Encryption
Cloud computing provides services rather than products; where it offers many benefits to clients who pay to use hardware and software resources. There are many advantages of using cloud computing such as low cost, easy t...
Big Data Strategy
The importance of data analysis in companies grows every day, with a global market that generates large amounts of transactions. Industry 4.0 is one of the technological trends, which is a set of diverse technologies who...
Control of Grid Connected Three-Phase Inverter for Hybrid Renewable Systems using Sliding Mode Controller
This paper presents a power control approach of a grid connected 3-phase inverter for hybrid renewable energy systems that consists of wind generator, flywheel energy storage system and diesel generator. A sliding contro...