Bit-stream recognition (BSR) has many applications, such as forensic investigations, detection of copyright infringement, and malware analysis. We propose the first BSR that takes a bare input bit-stream and outputs a class label without any preprocessing. To achieve our goal, we propose a centrifuge mechanism, where the upstream layers (sub-net) capture global features and tell the downstream layers (main-net) to switch the focus, even if a part of the input bit-stream has the same value. We applied the centrifuge mechanism to compiler provenance recovery, a type of BSR, and achieved excellent classification. Additionally, downstream transfer learning (DTL), one of the learning methods we propose for the centrifuge mechanism, pre-trains the main-net using the sub-net's ground truth instead of the sub-net's output. We found that sub-predictions made by DTL tend to be highly accurate when the sub-label classification contributes to the essence of the main prediction.
翻译:位流识别(BSR)有许多应用,例如法证调查、发现侵犯版权行为和恶意软件分析。我们建议第一种采用光输入位流的BSR,并产生一个没有预处理的分类标签。为了实现我们的目标,我们建议一个离心机机制,让上游层(子网)捕捉全球特征,并告诉下游层(大陆网)改变重点,即使输入位流的一部分具有同样的价值。我们应用离心机机制来收集来源,一种类型的BSR,并实现了极佳的分类。此外,下游传输学习(DTL),这是我们为离心机机制提议的学习方法之一,即利用子网的地面真相而不是子网的产出,在主网前对主网进行交易。我们发现,当子标签分类有助于主要预测的精髓时,DTL的子定位往往非常准确。