缓存心灵感应:利用共享资源攻击来学习DNN架构
Cache Telepathy: Leveraging Shared Resource Attacks to Learn DNN Architectures
摘要:
深度神经网络(DNN)因其在各种机器学习任务中获得良好准确性的能力而迅速变得无处不在。DNN的架构(即,它的超参数)广泛地决定了DNN的准确性和性能,并且通常是保密的。攻击云中的DNN以获取其架构可能会提供重大的商业价值。此外,获得DNN的架构有助于其他现有的DNN攻击。本文介绍了Cache Telepathy:一种使用缓存侧通道窃取DNN架构的快速准确机制。我们的攻击是基于DNN推理严重依赖于平铺GEMM(广义矩阵乘法)的见解,DNN架构参数决定了GEMM调用的数量和GEMM函数中使用的矩阵的维度。这样的信息可以通过高速缓存侧通道泄漏。本文使用Prime+Probe和Flush+ Proximad攻击运行OpenBLAS和英特尔MKL库的VGG和ResNet DNN。我们的攻击是有效的,通过大大减少目标DNN架构的搜索空间来帮助获得架构。例如,对于使用OpenBLAS的VGG,它将搜索空间从多于$10^{35}$架构减少到仅16。
英文摘要:
Deep Neural Networks (DNNs) are fast becoming ubiquitous for their ability to attain good accuracy in various machine learning tasks. A DNN's architecture (i.e., its hyper-parameters) broadly determines the DNN's accuracy and performance, and is often confidential. Attacking a DNN in the cloud to obtain its architecture can potentially provide major commercial value. Further, attaining a DNN's architecture facilitates other, existing DNN attacks. This paper presents Cache Telepathy: a fast and accurate mechanism to steal a DNN's architecture using the cache side channel. Our attack is based on the insight that DNN inference relies heavily on tiled GEMM (Generalized Matrix Multiply), and that DNN architecture parameters determine the number of GEMM calls and the dimensions of the matrices used in the GEMM functions. Such information can be leaked through the cache side channel. This paper uses Prime+Probe and Flush+Reload to attack VGG and ResNet DNNs running OpenBLAS and Intel MKL libraries. Our attack is effective in helping obtain the architectures by very substantially reducing the search space of target DNN architectures. For example, for VGG using OpenBLAS, it reduces the search space from more than $10^{35}$ architectures to just 16.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。