Table 2

Summary from literature review

RefMain ideaContributionTechniquesDataPerformanceRemarks
Sharif et al. (2008) Eureka framework for enabling static Internet malware binaries analysisCourse-grained execution tracker applying a heuristic based and a binary n-gram statistical trigger to estimate when to stop the malicious process imageAPI resolution techniques
IDA-Pro disassembler
De-obfuscation
Corpus of 1,291 malware instances, 479 malicious executables from spam traps, 435 malicious executables - Honeynet97.7% Spam malware corpus unpacking
93.3% honey net malware corpus unpacking
Unpacking of 90 binaries/hr
Automated classification of malware
Lengyel et al. (2014) DRAKVUF- dynamic MA systemImproves stealth by enforcing scalability, fidelity, stealth and isolation conserving resourcesHardware virtualization extensions and the Xen hypervisor1,000 samples from shadow serverMemory saving of 62.4%Automated classification of malware
Ucci et al. (2019) A survey on MA through machine learning techniquesNovel concept of MA economics, malware anti-analysis techniques, etc.A qualitative analysisProcessing one million malware per day86% accuracy using 3 as minimum n-grams sizeTuning strategies to balance metrics such as accuracy and cost in designing MA environment
Schultz et al. (2001) A data mining framework for automatically detecting new malicious binariesMethod for detecting previously undetectable malicious executablesNaive Bayes, multimodal-naive Bayes, RIPPER standard statistical cross-validationData set of 4,266 programmes 3,265 malicious binaries and 1,001 clean programmesMulti-naive Bayes yielded highest detection rate
97.76%
Extension of learning algorithms to make use of byte-sequences
Sethi et al. (2017) A framework for detecting and classifying malwareIntelligent MA framework
for dynamic and static analysis of malware samples based on similarity
J48, SMO and random forest
Cuckoo sandbox for malware analysis
220 Samples of malicious and benign files100%, 99% and 97% detection rate, and 100%, 91% and 66.67% classification, respectivelyData set of 220 samples needs to be expanded

or Create an Account

Close subscription notice
Close access options