Detection of Cyber-Physical Attacks in Additive Manufacturing: An LSTM-Based Autoencoder Method Utilizing Reconstruction Error Analysis from Side-Channel Monitoring
Journal Title: Engineering and Technology Journal - Year 2024, Vol 9, Issue 10
Abstract
To identify cyber-physical threats in additive manufacturing systems, this study proposes an advanced technique utilizing data from side-channel monitoring. The method combines several key approaches for preprocessing, analyzing, and classifying time-series data, ensuring robust attack detection capabilities. A predefined Window Sliding (FWS) preprocessing method segments continuous time-series data into manageable windows of specified size, making analysis more efficient. Next, we employ Discrete Wavelet Transform (DWT) to extract features from each window, capturing essential information across various frequency bands. Particle Swarm Optimization (PSO) is then used to refine the DWT coefficients, isolating the most valuable features to enhance classification performance by focusing on the most informative characteristics. The optimal feature set is used to train a deep learning (DL) model capable of identifying anomalies through reconstruction errors, specifically an LSTM-A autoencoder. Our results demonstrate that this approach can distinguish between normal and attack scenarios with an accuracy rate of 99% when applied to side-channel attack detection in additive manufacturing. This method provides a scalable and adaptable solution to safeguard cyber-physical systems against sophisticated cyberattacks while improving detection accuracy.
Authors and Affiliations
Dr. Ashish Khanna
Keywords
Related Articles
- EP ID EP749818
- DOI 10.47191/etj/v9i10.27
- Views 59
- Downloads 0
ADOPTING AND IMPLEMENTING PRACTICAL RELIABILITY TOOLS IN NIGERIA ELECTRIC POWER INDUSTRY
The dynamics of power plant operations and maintenance has changed drastically over the past decades. In the past, generation and supply of power to both the pub lic and industrial sectors was not competitive, partly bec...
CONTROL OF TWO MASS ELECTROMECHANICAL SYSTEM
In two-mass electromechanical system, the electromagnetic torque focuses on one (the first) mass. In that case, the second mass related with the first elastic link, can move through oscillating trajectory. The issue of t...
PARAMETRIC RISK ASSESSMENT OF INDUSTRIAL STORAGE TANKS
In the past, various damages have been observed in large number of industrial facilities during the experienced earthquakes. Different than the residential buildings, damages in industrial facilities have a significant d...
INVESTIGATION OF THE PYROLYSIS BEHAVIOUR OF MARINE MACROALGAE BIOMASS USING THE THERMOGRAVIMETRIC ANALYSIS
Macroalgae could be significant marine biomass resource for the production of numerous energy carriers including biofuels. In this research work, the kinetic characteristics of a red macroalgae, (Gelidium sesquipedale) a...
ROAD TRAFFIC MODELING: THE INTEREST OF WARM-UP DETECTION IN DYNAMIC SIMULATIONS
The design, study and management of road traffic systems has become increasingly difficult and costly as existing configurations are multiple and complex. Our objective in this article is to present a state of the art on...