arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2101.05646cs.CRcs.CLcs.LG
收藏

恶意代码检测:通过LSTM运行跟踪输出分析

Malicious Code Detection: Run Trace Output Analysis by LSTM

Informatics Institute, Middle East Technical University(中东技术大学信息学研究所)

Cengiz Acarturk, Melih Sirlanci, Pinar Gurkan Balikcioglu, Deniz Demirci, Nazenin Sahin, Ozge Acar Kucuk

摘要:

由于信息和通信技术在日常环境中的应用不断扩大,恶意软件威胁及其检测作为信息安全的一个子领域越来越重要。设计和开发反恶意软件系统的一个主要挑战是检测的覆盖范围,特别是动态分析方法的开发,可以有效地检测多态和变形恶意软件。在本研究中,我们提出了一个方法框架,通过分析运行轨迹输出的长短期记忆(LSTM)检测恶意代码。我们开发了恶意和良性的可移植可执行文件(PE)的运行轨迹模型。我们从PE文件的动态分析获得的运行跟踪输出创建了数据集。所获得的数据集是指令格式的序列,并被称为指令序列模型(ISM)。通过将第一个数据集分割成基本块,我们得到了第二个称为基本块作为序列模型(BSM)。实验结果表明,ISM的准确率为87.51%,假阳性率为18.34%,而BSM的准确率为99.26%,假阳性率为2.62%。

英文摘要:

Malicious software threats and their detection have been gaining importance as a subdomain of information security due to the expansion of ICT applications in daily settings. A major challenge in designing and developing anti-malware systems is the coverage of the detection, particularly the development of dynamic analysis methods that can detect polymorphic and metamorphic malware efficiently. In the present study, we propose a methodological framework for detecting malicious code by analyzing run trace outputs by Long Short-Term Memory (LSTM). We developed models of run traces of malicious and benign Portable Executable (PE) files. We created our dataset from run trace outputs obtained from dynamic analysis of PE files. The obtained dataset was in the instruction format as a sequence and was called Instruction as a Sequence Model (ISM). By splitting the first dataset into basic blocks, we obtained the second one called Basic Block as a Sequence Model (BSM). The experiments showed that the ISM achieved an accuracy of 87.51% and a false positive rate of 18.34%, while BSM achieved an accuracy of 99.26% and a false positive rate of 2.62%.

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。

↑