讲座时间：2022年6月23日星期四晚上7:00 pm -8:30 pm （北京时间）
主讲人：Shujie Cui, Lecturer, Monash University.
题目：Side-channel attacks and countermeasures on Intel SGX
内容简介：Intel SGX allows user processes to create trusted execution environments called enclaves, which protect security-sensitive computation against access from the OS kernel and the hypervisor. Recent work, however, has shown that Intel SGX is vulnerable to side-channel attacks that allow an adversary to learn secrets shielded in the enclave. The majority of such attacks trigger exceptions or interrupts to trace the control or data flow of enclave execution.
We propose STRONGBOX, a system that protects enclaves from side-channel attacks that interrupt enclave execution. The main idea behind STRONGBOX is to create an interrupt- free environment on a reserved CPU core for running enclaves in which enclaves destroy secrets and terminate when interrupts occur. STRONGBOX avoids interrupts by exploiting the tickless scheduling mode supported by recent Linux kernels. STRONGBOX then uses the state save area (SSA) of the enclave, which is used by the hardware to support interrupt handling, as a second stack. Through an LLVM-based compiler pass, STRONGBOX modifies enclave instructions to load/store data, such as function return addresses, from/to the SSA. When an interrupt occurs, the hardware overwrites the data in the SSA with CPU state, thus ensuring that the secrets are destroyed and enclave execution fails. Our performance evaluation shows that STRONGBOX significantly raises the bar for interrupts-based attacks with less than 20% overhead.
主讲人简介：Dr. Shujie Cui is a Lecturer at Monash University in the Faculty of Information Technology. She obtained her PhD degree from the University of Auckland in 2019. Before joining Monash University, she was a Post-Doc researcher in the Large-Scale Data & Systems (LSDS) group in the Department of Computing at Imperial College London, UK. Her main research interests include applied cryptography, information security in cloud computing and distributed systems, trusted execution environments, side-channel attacks, and privacy-preserving machine learning.