Cross-level Detection of Sensor-based Deception Attacks on Cyber-Physical Systems

Croteau, Brien; Krishnankutty, Deepak; Robucci, Ryan; Patel, Chintan; Banerjee, Nilanjan; Kiriakidis, Kiriakos; Rodriguez-Seda, Erick J.

doi:10.1109/cyber.2017.8446537

Cited by 4 publications

(7 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As mentioned earlier, [13] establishes the suitability of Gaussian PDF for these values. The null and alternate hypotheses correspond to f X (X|θ 0 ) and f X (X|θ 1 ), respectively.…”

Section: Cross-level Detectionmentioning

confidence: 99%

“…To determine a parameter of detection to combine with the macro-level detector, a simplified method utilizing the same FPGA hardware and collection method as [36] was proposed and verified [13]. A set of power supply current waveforms b k (n), where 0 < n < N max for N max observations over a certain window of clock cycles is collected when the sensor S i is operating in a known good (baseline) state and averaged together to form a reference where b gw (n) is the "golden waveform" generated from the point-wise average over the training set of M waveforms.…”

Section: Forming the Training Datamentioning

confidence: 99%

“…By virtue of the consensus network being connected and directed, the consensus value,ŷ c i , is an average of the initial states estimates [13] …”

Section: Reaching Consensus On Global State Estimatesmentioning

confidence: 99%

“…Per [13], ρ i follows Gaussian PDF N(m L , σ 2 L ). The median and variance of the metric for the null hypothesis was experimentally determined based on a large number of measurements of the correlation metric for test samples collected before the sensor node is deployed.…”

Section: Assessing Evidence Of Attackmentioning

confidence: 99%

“…The precursor of the present work is found in [13]. Therein, the authors presented the unified framework for combining the micro-and macro-level detectors, whose feasibility was illustrated in simplified experiments, respectively.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Cross-Level Detection Framework for Attacks on Cyber-Physical Systems

et al. 2017

Self Cite

View full text Add to dashboard Cite

Anomaly detection is critical in thwarting malicious attacks on Cyber-Physical Systems. This work presents a novel inference engine that integrates two heterogeneous anomaly detectors, working at different levels of the system architecture, in order to produce a crosslevel detector more effective than either one separately. The macro-or process-level detector uses a bank of observers of the physical plant that estimate the state of the process suspected to be under attack, specifically for its sensor to be compromised, from data gathered by available networked sensors. The estimates are then combined using a Weapons and Systems Engineering Department, U.S. Naval Academy, Annapolis, MD, USA consensus algorithm to determine if the suspect sensor is reporting false readings. The micro-level detector uses timesampled side-channel power measurements of an integrated circuit on the suspect sensor. By comparing power measurements against those from a known good state, differences indicate the code running inside has been altered. The crosslevel detector performs a two-dimensional Neyman-Pearson hypothesis test that declares the presence of an attack on the sensor node. The cross-level detector is shown to be more accurate and less latent than its constituent parts. Detection was tested against a range of False Data Injection attacks on a hardware prototype and the detector performance was measured experimentally. The cross-level detector on average achieved a 93% rate of correct detection, compared with 72 and 85% for the macro-and micro-level detectors, respectively; and a 50% reduction in latency compared to the macro-level detector.

show abstract

“…As mentioned earlier, [13] establishes the suitability of Gaussian PDF for these values. The null and alternate hypotheses correspond to f X (X|θ 0 ) and f X (X|θ 1 ), respectively.…”

Section: Cross-level Detectionmentioning

confidence: 99%

Section: Forming the Training Datamentioning

confidence: 99%

“…By virtue of the consensus network being connected and directed, the consensus value,ŷ c i , is an average of the initial states estimates [13] …”

Section: Reaching Consensus On Global State Estimatesmentioning

confidence: 99%

Section: Assessing Evidence Of Attackmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Cross-Level Detection Framework for Attacks on Cyber-Physical Systems

et al. 2017

Self Cite

View full text Add to dashboard Cite

show abstract

Deep Learning-Based Fault Prediction in Wireless Sensor Network Embedded Cyber-Physical Systems for Industrial Processes

et al. 2022

View full text Add to dashboard Cite

This paper investigates the challenging fault prediction problem in process industries that adopt autonomous and intelligent cyber-physical systems (CPS), which is in line with the emerging developments of industrial internet of things (IIoT) and Industry 4.0. Particularly, we developed an end-to-end deep learning approach based on a large volume of real-time sensory data collected from a chemical plant equipped with wireless sensors. Firstly, a novel recursive architecture with multi-lookback inputs is proposed to perform autoregression on imbalanced time-series data as a preliminary prediction. In this process, a novel learning algorithm named recursive gradient descent (RGD) is developed for the proposed architecture to reduce cumulative prediction uncertainties. Subsequently, a classification model based on temporal convolutions over multiple channels with decay effect is proposed to perform multi-class classification for fault root cause identification and localization. The overall network is named the cumulative uncertainty reduction network (CURNet), for its superior capacity in reducing prediction uncertainties accumulated over multiple prediction steps. Performance evaluations show that CURNet is able to achieve superior performance especially in terms of fault prediction recall and fault type classification accuracy, compared to the existing techniques.

show abstract

Virtual sensor forensics

Kebande

Ikuesan

2020

Proceedings of the 2nd International Conference on Intelligent and Innovative Computing Applications

View full text Add to dashboard Cite

Cross-level Detection of Sensor-based Deception Attacks on Cyber-Physical Systems

Cited by 4 publications

References 16 publications

Cross-Level Detection Framework for Attacks on Cyber-Physical Systems

Cross-Level Detection Framework for Attacks on Cyber-Physical Systems

Deep Learning-Based Fault Prediction in Wireless Sensor Network Embedded Cyber-Physical Systems for Industrial Processes

Virtual sensor forensics

Contact Info

Product

Resources

About