BULKOR: Enabling Bulk Loading for Path ORAM
Xiang Li, Yunqian Luo, Mingyu Gao
IEEE Symposium on Security and Privacy 2024 · Day 3 · Continental Ballroom 6
In an era where cloud computing is ubiquitous, the security of sensitive data processed in remote environments is a paramount concern. While **Trusted Execution Environments (TEEs)** like Intel SGX and AMD SEV offer hardware-backed isolation to protect data and code from a compromised host, they are not impervious to side-channel attacks, particularly those exploiting **access patterns**. This talk, "BULKOR: Enabling Bulk Loading for Path ORAM," presented by Xiang Li, Yunqian Luo, and Mingyu Gao, addresses a critical bottleneck in deploying **Oblivious RAM (ORAM)**, a cryptographic primitive designed to hide access patterns, within these TEEs: the inefficiency of ORAM initialization, or "bulk loading."
AI review
This research annihilates the critical bottleneck of ORAM bulk loading in TEEs, a problem that has plagued practical deployment for years. BULKOR's novel `O(N log N)` algorithm achieves up to 160x speedup, transforming ORAM from a theoretical ideal into a deployable defense against access pattern side channels. This work is a fundamental enabler for secure cloud computation.