A Lightweight and Real-Time Hardware Architecture for Interference Detection and Mitigation of Time Synchronization Attacks Based on MLP Neural Networks

Orouji, Niloofar; Mosavi, Mohammad Reza; Martín, Diego

doi:10.1109/access.2021.3120668

Cited by 5 publications

(2 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are numerous researches and studies to mitigate the effects of such TSAs. An MLP NN that detects TSAs and compensates the clock offset errors is proposed by the authors of this research [24,25]. Furthermore, a tuning-free, low memory, and robust estimator can effectively reduce the effects of the proposed TSA [1].…”

Section: Discussionmentioning

confidence: 99%

Evaluation of GPS Signal Vulnerabilities against Time Synchronization Attacks

Bagheri

Orouji

Mosavi

2023

Preprint

Self Cite

View full text Add to dashboard Cite

A spoofing attack is an intervention aimed at forcing the GPS receiver to obtain and track invalid navigation data. Time Synchronization Attack (TSA) is a type of spoofing attack that changes the receiver clock information, such as clock offset and drift. The purpose of TSA is to create an error in the estimated time of the receiver. These attacks usually target static receivers that use GPS signals for their time-synchronization applications. One of the main countermeasures for any security vulnerabilities is comprehending the process of thread generation and weak points of the system. In this research, for the first time, the TSA generation process is discussed and explained in detail. The proposed method demonstrates the feasibility of a spoof attack on the GPS receiver. The attack is defined as an optimization problem that aims to maximize the receiver clock offset error while maintaining the receiver position. The decision variables in the optimization problem are the coordinates of the receiver and the satellite's ephemerides variables. The constraints are such that the decision variables and satellite positions calculated from solving the optimization problem are close to pre-attack values to avoid possible detection schemes that examine large mutations in the values of these variables. Due to the ability to solve complex problems, simple concepts, and easy implementation of Metaheuristic Optimization Algorithms (MOA), Chimp Optimization Algorithm (ChoA), Grey Wolf Optimization (GWO) and Particle Swarm Optimization (PSO) algorithms are exploited. According to the achieved solutions, the maximum modification in the receiver clock offset is 1.6 ms, which is a severe attack based on IEEE C37.118 standard. This result is achieved despite a change of 10 meters in the coordinates of the receiver position.

show abstract

Section: Discussionmentioning

confidence: 99%

Evaluation of GPS Signal Vulnerabilities against Time Synchronization Attacks

Bagheri

Orouji

Mosavi

2023

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…There are five categories of AF based on [1], namely bounded, rectified, non-linear below, non-linear and unbounded above, and increasing and decreasing functions. The sigmoid function is a bounded function broadly used in many FNN applications [11,16,23,28]. It is a smooth and continuous function that maps real value [−∞, ∞] into [0, 1] [7].…”

Section: Introductionmentioning

confidence: 99%

The effect of amplitude modification in S-shaped activation functions on neural network regression

Makhrus

2023

NNW

View full text Add to dashboard Cite

Time series forecasting using multilayer feed-forward neural networks (FNN) is potential to give high accuracy. Several factors influence the accuracy. One of them is the choice of activation functions (AFs). There are several AFs commonly used in FNN with their specific characteristics, such as bounded type AFs. They include sigmoid, softsign, arctan, and tanh. This paper investigates the effect of the amplitude in the bounded AFs on the FNNs accuracy. The theoretical investigations use simplified FNN models: linear equation and linear combination. The results show that the higher amplitudes give higher accuracy than typical amplitudes in softsign, arctan, and tanh AFs. However, in sigmoid AF, the amplitude changes do not influence the accuracy. These theoretical results are supported by experiments using the FNN model for time series prediction of 10 foreign exchanges from different continents compared to the US dollar. Based on the experiments, the optimum amplitude of the AFs should be high, that is greater or equal to 100 times of the maximum input values to the FNN, and the accuracy gains up to 310 times.

show abstract

FPGA-Type Configurable Coprocessor Implementation Scheme of Recurrent Neural Network for Solving Time-Varying QP Problems

Zhang

Deng

et al. 2022

IEEE Trans. Circuits Syst. I

View full text Add to dashboard Cite

A Lightweight and Real-Time Hardware Architecture for Interference Detection and Mitigation of Time Synchronization Attacks Based on MLP Neural Networks

Cited by 5 publications

References 35 publications

Evaluation of GPS Signal Vulnerabilities against Time Synchronization Attacks

Evaluation of GPS Signal Vulnerabilities against Time Synchronization Attacks

The effect of amplitude modification in S-shaped activation functions on neural network regression

FPGA-Type Configurable Coprocessor Implementation Scheme of Recurrent Neural Network for Solving Time-Varying QP Problems

Contact Info

Product

Resources

About