Machine learning models have achieved great success and have been deployed prominently in many real-world applications. However, the sensitive nature of individual users’ data has also raised privacy concerns against machine learning. A recent thread of research has shown that a malicious adversary can infer private information of users’ data by querying target machine learning models.
Final Public Orals
- Thu, Sep 16, 2021, 2:00 pm
- Thu, Sep 9, 2021, 9:30 am
Recent years have witnessed the rapid development of deep learning in many domains. These successes inspire using deep learning in the area of security. However, there are at least two main challenges when security meets deep learning. First, the deep learning systems themselves are vulnerable to various attacks, bringing new concerns when using deep learning to improve security in computer systems. Second, the availability of attack data is a problem.
- Fri, Aug 20, 2021, 10:00 am
Contributing to the rising popularity of computational social science, this dissertation presents new methods grounded in machine learning for solving several important problems in political science.
- Thu, Aug 29, 2019, 11:00 am
Wireless communication is undergoing a fundamental transformation as the new spectrum in the millimeter-wave (mm-Wave) frequencies (30-300 GHz) opens up to serve as the backbone for the next-generation wireless infrastructure. The application range is expected to be extremely heterogeneous ranging from extremely high-speed cellular connectivity, automotive-to-anything (V2x), augmented reality (AR), virtual reality (VR) to wireless backhaul and last mile connectivity.
- Thu, Jun 27, 2019, 10:30 am to 12:00 pm
Device scaling, an enabler of faster and more powerful processors for decades, has become challenging due to physical limits and manufacturing costs. Thus, we need newer approaches for low-power and high-performance designs for next generation computing technologies. In this talk, we focus on FinFET-based static random access memory (SRAM) and hybrid monolithic 3-D integrated circuit (IC) design.
- Fri, Jun 7, 2019, 11:00 am to 12:30 pm
- Fri, May 17, 2019, 10:00 am to 11:30 am
- Thu, May 16, 2019, 1:30 pm to 3:00 pm
- Thu, May 16, 2019, 10:30 am to 12:00 pm
- Thu, May 16, 2019, 9:00 am to 10:30 am
As demand for cheap, carbon-neutral energy continues to grow, so too does the search for novel photovoltaic technologies that can complement or outperform silicon. Thin film organic and metal-halide perovskite materials are ideal candidates for thin, flexible, or transparent solar cells and may even serve as a cheap tandem layer to boost the efficiency of traditional silicon cells. Organic and perovskite solar cell efficiencies have grown rapidly, yet knowledge of the electronic states within these systems is necessary to continue this trend.