Document Type



Master of Science (MS)


Computer Engineering

First Advisor's Name

Mohammad Ashiqur Rahman

First Advisor's Committee Title

Committee chair

Second Advisor's Name

A. Selcuk Uluagac

Second Advisor's Committee Title

committee member

Third Advisor's Name

Sumit Paudyal

Third Advisor's Committee Title

committee member


Deception, Defense, Cyber-physical systems, Power Grids, MTD, Machine Learning

Date of Defense



Cyber-physical Systems (CPSs) and the Internet of Things (IoT) are converging towards a hybrid platform that is becoming ubiquitous in all modern infrastructures. The integration of the complex and heterogeneous systems creates enormous space for the adversaries to get into the network and inject cleverly crafted false data into measurements, misleading the control center to make erroneous decisions. Besides, the attacker can make a critical part of the system unavailable by compromising the sensor data availability. To obfuscate and mislead the attackers, we propose DDAF, a deceptive data acquisition framework for CPSs' hierarchical communication network. Each switch in the hierarchical communication network generates a random pattern of addresses/IDs by shuffling the original sensor IDs reported through it. During the data acquisition from remotely located sensors to the central controller, the switches craft the network packets by replacing a few sensors' associated addresses/IDs with the generated deceptive IDs and by adding decoy data for the rest.

While misleading the attackers, the control center must retrieve the actual data to operate the system correctly. We propose three remapping mechanisms (e.g., seed-based, prediction-based, and hybrid) and compare their robustness against different stealthy attacks. Due to the deception, artfully altered measurements turn into random data injections, making it easy to remove them as outliers. As the outliers and the estimated residuals contain the potential attack vectors, DDAF can detect and localize the attack points and the targeted sensors by analyzing this information. DDAF is generic and scalable to be implemented in any hierarchical CPSs network. Experimental results on the standard IEEE 14, 57, and 300 bus power systems show that DDAF can detect, mitigate, and localize up-to 100% of the stealthy cyberattacks. To the best of our knowledge, this is the first framework that implements complete randomization in the data acquisition of the hierarchical CPSs.





Rights Statement

Rights Statement

In Copyright. URI:
This Item is protected by copyright and/or related rights. You are free to use this Item in any way that is permitted by the copyright and related rights legislation that applies to your use. For other uses you need to obtain permission from the rights-holder(s).