Quantum Machine Learning in Science and Cybersecurity
Disciplines
Engineering
Abstract (300 words maximum)
Quantum machine learning has the potential to revolutionize cybersecurity by enabling more precise threat detection across massive datasets, and to explore this potential, our team—composed of Cliff Russell, Hayden Agnew, and Josiah Sado—aims to determine whether a quantum-enhanced model can more effectively detect malicious activities within IBM’s Nutch logs compared to conventional approaches. By focusing on suspicious patterns in both raw and processed logs, we plan to train a quantum-based machine learning system on a carefully filtered dataset and measure its detection accuracy, speed, and scalability against established benchmarks. Preliminary results suggest that quantum methodologies may reduce false positives and uncover hidden anomalies more efficiently, thereby bridging the gap between emerging quantum science and real-world cybersecurity. Ultimately, these findings could lead to more robust and proactive threat detection strategies in both scientific and commercial domains.
Academic department under which the project should be listed
SPCEET - Electrical and Computer Engineering
Primary Investigator (PI) Name
Yong Shi
Quantum Machine Learning in Science and Cybersecurity
Quantum machine learning has the potential to revolutionize cybersecurity by enabling more precise threat detection across massive datasets, and to explore this potential, our team—composed of Cliff Russell, Hayden Agnew, and Josiah Sado—aims to determine whether a quantum-enhanced model can more effectively detect malicious activities within IBM’s Nutch logs compared to conventional approaches. By focusing on suspicious patterns in both raw and processed logs, we plan to train a quantum-based machine learning system on a carefully filtered dataset and measure its detection accuracy, speed, and scalability against established benchmarks. Preliminary results suggest that quantum methodologies may reduce false positives and uncover hidden anomalies more efficiently, thereby bridging the gap between emerging quantum science and real-world cybersecurity. Ultimately, these findings could lead to more robust and proactive threat detection strategies in both scientific and commercial domains.