I’m an Assistant Professor in the Department of Computer Science at Illinois Institute of Technology. I am leading the Emerging Computing Systems (ECS or X) Lab. My research interest includes computer architecture, software-hardware co-design, emerging memory/storage technologies, machine learning acceleration, and privacy-preserving computing.

Prospective students: I am actively looking for self-motivated students at all levels for various research projects in the fields of computer architectures, systems, compilers, software-hardware co-design, privacy-preserving computing, and machine learning. The projects will involve active collaborations with UCSD, UIUC, ETH Zurich, UT Dallas, Intel Labs, IBM Research, and other groups at IIT. If you are interested in working with me, please send an email with a subject of “Potential Student” to mzhou26 at iit dot edu.

Detailed Research Areas

Software-Hardware Co-Design for Emerging Applications

Software-hardware co-design refers to the collaborative design process where both software and hardware components are developed simultaneously to optimize overall system performance, efficiency, and functionality. This integrated approach is particularly critical in emerging applications that involve complex and data-intensive workloads, high performance requirements, and rapidly evolving technology landscapes. Applications such as artificial intelligence (AI), machine learning (ML), Internet of Things (IoT), autonomous systems, edge computing, bioinformatics, and cryptographyh demand highly efficient, customizable, and power-efficient hardware-software solutions. This research aims to develop novel algorithms, system supports, and hardware architectures to tackle the fundanmental bottleckneck of emerging applications on current systems and achieves significant improvements on performance and energy efficiency.

Non-Conventional Computer Architecture

Non-conventional computer architectures represent a significant departure from traditional von Neumann architectures, which are built around the idea of a central processor (CPU), memory, and input/output devices. Emerging application domains, such as artificial intelligence (AI), machine learning (ML), quantum computing, edge computing, and the Internet of Things (IoT), often demand more specialized, efficient, and scalable computing systems that are not well-served by conventional architectures. These applications require alternative computational models, novel hardware designs, and innovative approaches to data processing, leading to the rise of non-conventional computer architectures. This research aims to innovate computer architecture designs with the consideration of emerging applications and hardware technologies. This research also includes the system development to enable the usage of non-conventional architectures in real-world computing.

Privacy-Preserving Computing

Privacy-preserving computing aims to protect sensitive data while still enabling computation on it, a key concern in today’s data-driven world. As organizations and individuals generate vast amounts of personal and sensitive information, there is a pressing need to ensure that data privacy is maintained while still allowing for useful computations, such as analytics, machine learning, and secure data sharing. Traditional privacy models, where data is kept private by simply encrypting it or restricting access, are no longer sufficient as new applications demand that computations be performed on encrypted or distributed data without compromising privacy. This has led to the development of advanced cryptographic techniques that enable privacy-preserving computation (PPC), allowing computations to be carried out without exposing sensitive information. Notable cryptographic protocols in this domain include Fully Homomorphic Encryption (FHE), Zero-Knowledge Proofs (ZKPs), and Garbled Circuits. These protocols allow for secure computation in settings where data needs to remain private, such as in cloud computing, collaborative data analysis, and federated machine learning. This research focuses on two critical aspects for privacy-preserving computing: 1. developing novel hardware to significantly improve the computing efficiency of privacy-preserving computing, and 2. developing novel software tools to adopt privacy-preserving computing for real-world applications.