CNS Core: Small: Practical Memory Access Pattern Obfuscation with Algorithm, Application and Architecture Co-designs

点击翻译按钮获取中文摘要

Emerging memory architectures are proposed to address the scalability issues of current computing systems. However, they bring challenges when data security support is needed. An attacker could capture sensitive information in a program through side channels, such as memory access patterns. Moreover, emerging memory systems further complicate security support due to the new properties such as larger sharing space, data persistency, and concurrent accesses. This research aims to enable high-performance and practical memory access pattern obfuscation for current and emerging memory architectures. The approaches include co-designs from the cryptographic algorithms, target applications that need protection, and new memory architectures. The success of this project can keep improving the performance of cryptographic protocols on real computing systems and applications. The outcome will include a set of integrated, cross-domain secure architecture designs and obfuscation schemes. The project outcomes will have significant broader impacts on education, society, and national security. This project will broaden computing participation by recruiting undergraduate researchers and outreach to underrepresented groups. With a closer interaction between security and computer architecture, the proposed research will benefit a broader type of applications and thus help protect national security in the long run.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.