Physical Sciences and Mathematics Commons^™

Secure And Efficient Federated Learning, Xingyu Li

Theses and Dissertations

In the past 10 years, the growth of machine learning technology has been significant, largely due to the availability of large datasets for training. However, gathering a sufficient amount of data on a central server can be challenging. Additionally, with the rise of mobile networking and the large amounts of data generated by IoT devices, privacy and security issues have become a concern, resulting in government regulations such as GDPR, HIPAA, CCPA, and ADPPA. Under these circumstances, traditional centralized machine learning methods face a problem in that sensitive data must be kept locally for privacy reasons, making it difficult to …

Challenges In Large-Scale Machine Learning Systems: Security And Correctness, Emad Alsuwat

Theses and Dissertations

In this research, we address the impact of data integrity on machine learning algorithms. We study how an adversary could corrupt Bayesian network structure learning algorithms by inserting contaminated data items. We investigate the resilience of two commonly used Bayesian network structure learning algorithms, namely the PC and LCD algorithms, against data poisoning attacks that aim to corrupt the learned Bayesian network model.

Data poisoning attacks are one of the most important emerging security threats against machine learning systems. These attacks aim to corrupt machine learning models by con- taminating datasets in the training phase. The lack of resilience of …

Securing Critical Infrastructure: A Ransomware Study, Blaine M. Jeffries

Theses and Dissertations

This thesis reviews traditional ransomware attack trends in order to present a taxonomy for ransomware targeting industrial control systems. After reviewing a critical infrastructure ransomware attack methodology, a corresponding response and recovery plan is described. The plan emphasizes security through redundancy, specifically the incorporation of standby programmable logic controllers. This thesis goes on to describe a set of experiments conducted to test the viability of defending against a specialized ransomware attack with a redundant controller network. Results support that specific redundancy schemes are effective in recovering from a successful attack. Further experimentation is conducted to test the feasibility of industrial …