The security vulnerabilities of off-chip memory can undermine the confidentiality and integrity necessary for deep neural network (DNN) accelerators that process private data and make critical decisions. This work illustrates such vulnerabilities and proposes an effective, hardware-friendly defense solution that provides memory security for DNN accelerators.
Speaker
Kyungmi Lee
Kyungmi Lee received a Ph.D. degree in Electrical Engineering and Computer Science from MIT in May 2024. She is currently a Postdoctoral Associate at Prof. Anantha Chandrakasan’s group. Her research interests are security and energy-efficiency of machine learning hardware systems.
Explore
New 3D Chips could Make Electronics Faster and more Energy-Efficient
Adam Zewe | MIT News
The low-cost, scalable technology can seamlessly integrate high-speed gallium nitride transistors onto a standard silicon chip.
Anantha Chandrakasan Named MIT Provost
Kathy Wren | MIT News
A faculty member since 1994, Chandrakasan has also served as dean of engineering and MIT’s inaugural chief innovation and strategy officer, among other roles.
Photonic Processor could Streamline 6G Wireless Signal Processing
Adam Zewe | MIT News
By performing deep learning at the speed of light, this chip could give edge devices new capabilities for real-time data analysis.