System Statistics Learning-Based IoT Security: Feasibility and Suitability

Li, Fangyu; Shinde, Aditya; Shi, Yang; Ye, Jin; Li, Xiangyang; Song, Wen-Zhan

doi:10.1109/jiot.2019.2897063

Cited by 77 publications

(54 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the normal distribution power grids, the voltages and currents should be stable. If abnormal changes happen to ∆V n and ∆I np , an event can be detected based on certain thresholding methods [23], [24]. Here, instead of directly using the difference, we treat it as one dimension of the high-dimensional detection metrics matrix.…”

Section: B Feature Extractionmentioning

confidence: 99%

Detection and Identification of Cyber and Physical Attacks on Distribution Power Grids With PVs: An Online High-Dimensional Data-Driven Approach

Xie

Yang

et al. 2022

IEEE J. Emerg. Sel. Topics Power Electron.

Self Cite

View full text Add to dashboard Cite

Cyber and physical attacks threaten the security of distribution power grids. The emerging renewable energy sources such as photovoltaics (PVs) introduce new potential vulnerabilities. Based on the electric waveform data measured by waveform sensors in the distribution power networks, in this paper, we propose a novel high-dimensional data-driven cyber physical attack detection and identification approach (HCADI). Firstly, we analyze the cyber and physical attack impacts (including cyber attacks on the solar inverter causing unusual harmonics) on electric waveforms in distribution power grids. Then, we construct a high dimensional streaming data feature matrix based on signal analysis of multiple sensors in the network. Next, we propose a novel mechanism including leverage score based attack detection and binary matrix factorization based attack diagnosis. By leveraging the data structure and binary coding, our HCADI approach does not need the training stage for both detection and the root cause diagnosis, which is needed for machine learning/deep learning-based methods. To the best of our knowledge, it is the first attempt to use raw electrical waveform data to detect and identify the power electronics cyber/physical attacks in distribution power grids with PVs.

show abstract

Section: B Feature Extractionmentioning

confidence: 99%

Detection and Identification of Cyber and Physical Attacks on Distribution Power Grids With PVs: An Online High-Dimensional Data-Driven Approach

Xie

Yang

et al. 2022

IEEE J. Emerg. Sel. Topics Power Electron.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Recurrent neural networks (RNN) is a type of deep neural network (DNN). With the internal memory unit, RNN can better capture the signal dynamics, which is important for the time-series data analytics [162]- [164]. Convolutional neural network (CNN) is another type of DNN which is widely used for image processing.…”

Section: Data-driven Cyber-attack Detection and Mitigationmentioning

confidence: 99%

Cyber–Physical Security of Powertrain Systems in Modern Electric Vehicles: Vulnerabilities, Challenges, and Future Visions

You-hai

Guo

Yang

et al. 2021

IEEE J. Emerg. Sel. Topics Power Electron.

Self Cite

View full text Add to dashboard Cite

“…There are also some works that focus on learning-based IoT security. For example, [9] proposed to apply statistical learning methods to detect anomalies in the behaviors of IoT devices. They based their statistical analysis in CPU usage cycles and disk usage through IoT application program interfaces.…”

Section: B Machine Learning In Iot Securitymentioning

confidence: 99%

Defenses Against Perception-Layer Attacks on IoT Smart Furniture for Impaired People

2020

View full text Add to dashboard Cite

Internet of Things (IoT) is becoming highly supportive in innovative technological solutions for assisting impaired people. Some of these IoT solutions are still in a prototyping phase ignoring possible attacks and the corresponding security defenses. This article proposes a learning-based approach for defending against perception-layer attacks performed on specific sensor types in smart furniture for impaired people. This approach is based on the analysis of time series by means of dynamic time warping algorithm for calculating similarity and a novel detector for identifying anomalies. This approach has been illustrated by defending against simulated perception-layer magnetic attacks on a smart cupboard with door magnetic sensors. The results show the performance of the proposed approach for properly identifying these attacks. In particular, these results advocate an accuracy about 95.5% per day.

show abstract

System Statistics Learning-Based IoT Security: Feasibility and Suitability

Cited by 77 publications

References 26 publications

Detection and Identification of Cyber and Physical Attacks on Distribution Power Grids With PVs: An Online High-Dimensional Data-Driven Approach

Detection and Identification of Cyber and Physical Attacks on Distribution Power Grids With PVs: An Online High-Dimensional Data-Driven Approach

Cyber–Physical Security of Powertrain Systems in Modern Electric Vehicles: Vulnerabilities, Challenges, and Future Visions

Defenses Against Perception-Layer Attacks on IoT Smart Furniture for Impaired People

Contact Info

Product

Resources

About