Driving Innovation Through Scalable Backend & Deep Tech Solutions.
This paper tackles cybersecurity challenges in battery health monitoring systems within networked environments. It introduces an adversarial attack on such systems and puts forth a Quantum Boost (QBoost)-based algorithm, expertly trained on the D-Wave Quantum Annealing (QA) processor, to effectively counteract these cyber threats. The QBoost methodology exhibits remarkable resilience against adversarial attacks when juxtaposed with the Random Forest (RF)-based approach, while RF excels in standard operational scenarios. Furthermore, comprehensive optimization details of the QBoost algorithm are elaborated upon in the complete paper.
In light of growing cybersecurity concerns surrounding smart grid devices, this paper presents an innovative cloud-based solution for detecting malware. This system leverages advanced technology, including a quantum-convolutional neural network (QCNN) with deep transfer learning (DTL), to effectively identify malware in various smart grid devices. The implementation on the IBM Watson Studio platform, powered by IBM Quantum processing, demonstrates significant improvements in detecting malicious files when compared to traditional CNN methods.
Check out some of my personal and paid projects