Quantum-Enhanced Hybrid Deep Learning Framework for Robust Audio Deepfake Detection (2025)
Al Amin
The recent proliferation of audio deepfakes poses significant threats to cybersecurity, media integrity, and public trust. Traditional detection methods struggle with real-time applicability, adversarial robustness, and forensic compliance. This research addresses these challenges by proposing a quantum-enhanced hybrid model integrating CNNs, RNNs, Transformers, and quantum computing techniques. Specifically, the framework targets improved feature separability, enhanced adversarial robustness, scalability, and compliance with forensic standards.
Big Data Analytics for high dimensional and heterogeneous datasets (2016)
Vandana Janeja, Information Systems
Akshay Grover
Jay Gholap
With the diversity and amounts of data increasing there is an increasing need to evaluate big data frameworks and how well they adapt to analytics techniques. In this project we will evaluate the performance of big data solutions across multiple analytic approaches. Publicly available healthcare data will be utilized as a test bed where analytics techniques, particularly ensemble based learning will be evaluated. Key parameters will be measured including algorithmic outcomes (such as diversity and size of training samples), usability, adaptability and modularity, robustness and efficiency.
Change detection in evolving communication networks (2016)
The process of network evolution describes changes in the behavior of a network structure. However, defining what is changing in large computer networks can be challenging especially when dealing with numerous nodes involved in large volumes of traffic flows over multiple periods of time. Therefore, studying an evolving computer network can be used to determine what exactly is changing in the network. Such changes in traffic can be defined in terms of sudden absence of key nodes or edges, or the addition of new nodes and edges to the network. These are micro level changes. This on the other hand may lead to changes at the macro level of the network such as changes in the density and diameter of the network that describe connectivity between nodes as well as flow of information within the network. Most importantly, observing a network’s behavior at different points in time can be used to determine the time when such changes occurred. We refer to such a changing network as a temporally evolving computer network.