Active Learning-Based XGBoost for Cyber Physical System Against Generic AC False Data Injection Attacks

Abstract

With the exponential growth of information and communication technology, the traditional power system is gradually evolving into a cyber physical energy system (CPES) with frequently interactions between physical and cyber components. CPES indeed revolutionize the power grid efficiency and operational performance, but it also gives rise to new security challenges, causing catastrophic consequences in power system. Therefore, this paper proposes a new false data injection attack (FDIA) detection mechanism to automatically recognize the intrusions and thereby improve the cybersecurity of CPES. In this mechanism, a two-stage FDIA model is developed to generate training dataset for the machine learning-based detector, and an extreme gradient boosting (XGBoost) classifier is meticulously designed by combining with active learning and Bayesian optimization techniques to improve training efficiency and model performance respectively. The proposed FDIA defense strategy can properly extract the nonstationary and nonlinear attacking features and thus locate the biased states with a high accuracy. The obtained numerical results on the standard IEEE 14-, 57-and 118-bus systems highlight the destructive effects of the developed two-stage FDIA and comprehensively demonstrate the effectiveness of the proposed FDIA detection mechanism. INDEX TERMS Cyber physical energy system (CPES), false data injection attack (FDIA), extreme gradient boosting (XGBoost), FDIA defense strategy.

AI Driven False Data Injection Attack Recognition Approach for Cyber-Physical Systems in Smart Cities

“…A defensive algorithm of inversing a linear forward attack by evaluating with minimum mean squared or least square approach is introduced. Xue and Wu [18] suggested an innovative FDIA identification algorithm for automatic IDS and therefore, enhancing the cyber security of CPES. This method has been a 2-stages FDIA algorithm that could be introduced to produce trained datasets for the ML-based detector, and the XGBoost classifier has been accurately developed by incorporating Bayesian optimizer and active learning approaches to increase training and model performances respectively.…”

Collaborative Filtering Recommendation of Music MOOC Resources Based on Spark Architecture

“…According to their common scoring results, it is regarded as the limited order of personalized recommendation for dynamic users in big data. XGBoost algorithm is a learning system based on tree structure [ 25 ]. Compared with commonly used advanced algorithms, such as ant colony algorithm and fish swarm algorithm, the XGBoost algorithm has good scalability and scalability.…”

A New False Data Injection Attack Detection Model for Cyberattack Resilient Energy Forecasting

“…Al-Abassi et al [23] presented an ensemble deep learning-based FDI attack detection mechanism for the industrial control systems. Xue and Wu [24] introduced a new active learning-based FDI attack detection method for the cyber-physical systems. Besides, general regression neural networks [25], deep belief networks [26], reinforcement learning [27], long short term memory networks [28], and support vector machines [29] have also been used on the task of FDI attack detection.…”