Doctor of Philosophy (Ph.D.)
Degree Granting Department
Zhuo Lu, Ph.D.
Mahshid Rahnamay Naeini, Ph.D.
Jay Ligatti, Ph.D.
Kwang-Cheng Chen, Ph.D.
Kaiqi Xiong, Ph.D.
Adversarial Machine Learning, Attacks and Defenses, Binary Code Similarity Detection, Cognitive Radio Networks, Cybersecurity, High Performance Computing
Security of real-world cyber systems has drawn a lot of attention in recent years, especially when machine learning techniques are widely deployed into different layers of cyber systems. With the technology of machine learning, especially adversarial machine learning techniques, the attacks and defenses in cyber systems have shown a lot of new characteristics. In this dissertation, two major works regarding the attacks and defenses in real world cyber systems including dynamic spectrum sensing systems and High Performance Computing (HPC) systems and software systems are discussed.
In the first work, we revisit this security vulnerability of cooperative spectrum sensing as an adversarial machine learning problem and propose a novel learning-empowered framework named Learning-Evaluation-Beating (LEB) to mislead fusion centers. Given the gap between the new LEB attack and existing defenses, we introduced a non-invasive and parallel method named influence-limiting defense sided with existing defenses to defend against LEB-based or other similar attacks.
In the second work, we offer a novel perspective, treating the anomaly detection in HPC systems based on log files as a sequential decision process, and further applying reinforcement learning techniques to detect anomalies or malicious users. Start from there, we also provide a binary code similarity detection-based method that can be applied to a more general scenario in software systems through utilizing Recurrent Neural Network (RNN) and Siamese Neural Network to detect malwares from the binaries generated by the processor that executing the program.
Scholar Commons Citation
Luo, Zhengping, "Security Attacks and Defenses in Cyber Systems: From an AI Perspective" (2021). Graduate Theses and Dissertations.