Attacking memory-hard scrypt with near-data-processing
Attacking memory-hard scrypt with near-data-processing
复制标题
DOI：
10.1145/3357526.3357570
复制
发表时间：
2019-09
期刊：
影响因子：
--
通讯作者：
Jiwon Choe;T. Moreshet;R. Iris Bahar;Maurice Herlihy
中科院分区：
文献类型：
--
作者：
Jiwon Choe;T. Moreshet;R. Iris Bahar;Maurice Herlihy
在传统的基于DRAM的主存储器架构中，存储器访问操作比简单的逻辑操作需要更多的时间和精力。利用这一事实来构建耗时且耗电的硬内存加密函数，以达到阻止暴力安全攻击的目的。这种内存困难函数的安全性完全取决于内存访问的不平凡成本。然而，最近出现了各种具有计算能力的内存技术，作为减少内存访问瓶颈的有前途的方法，但没有人研究它们如何影响内存硬加密功能的安全性。在这项初步工作中，我们研究了近数据处理 (NDP) 对 scrypt（一种广泛使用的基于内存硬密码的密钥派生函数）的影响，并讨论了使用可计算内存进一步破坏 scrypt 的机会。
In a traditional DRAM-based main memory architecture, a memory access operation requires much more time and energy than a simple logic operation. This fact is exploited to build time-consuming and power-hungry memory-hard cryptographic functions that serve the purpose of hindering brute-force security attacks. The security of such memory-hard functions depends entirely on the non-trivial costs of memory access. However, various compute-capable memory technologies have recently emerged as promising ways to reduce the memory access bottleneck, yet no one has looked into how they may impact the security of memory-hard cryptographic functions. In this preliminary work, we investigate the impact of near-data-processing (NDP) on scrypt, a widely used memory-hard password-based key-derivation function, and discuss the opportunities to further undermine scrypt using compute-capable memory.