学习自动从AI程序中反向DNN
Learning to Reverse DNNs from AI Programs Automatically
摘要:
随着DNN在边缘设备上的私有化部署,设备上DNN的安全性引起了人们的极大关注。为了自动量化设备上DNN的模型泄漏风险,我们提出了NNReverse,这是第一种基于学习的方法,可以在没有领域知识的情况下从AI程序中反向DNN。NNReverse训练表示模型来表示DNN层的二进制代码的语义。通过在我们的数据库中搜索最相似的函数,NNReverse推断出给定函数的二进制代码的层类型。为了精确地表示汇编指令语义,NNReverse提出了一种更细粒度的嵌入模型来表示汇编函数的文本和结构语义。
英文摘要:
With the privatization deployment of DNNs on edge devices, the security of on-device DNNs has raised significant concern. To quantify the model leakage risk of on-device DNNs automatically, we propose NNReverse, the first learning-based method which can reverse DNNs from AI programs without domain knowledge. NNReverse trains a representation model to represent the semantics of binary code for DNN layers. By searching the most similar function in our database, NNReverse infers the layer type of a given function's binary code. To represent assembly instructions semantics precisely, NNReverse proposes a more fine-grained embedding model to represent the textual and structural-semantic of assembly functions.
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。