The Computer Journal · 2020 · 12 citations · 14 references
ComputingComputer ScienceCybersecurityFeature EngineeringInternet Of ThingsMalware AnalysisFlow Feature ExtractionIot SecurityAccuracyControl Flow Graph AnalysisFlow-based DetectionIot Malware DetectionMalware Feature ExtractionNp-hardnessPolynomial Time ComplexityPolynomial-time Algorithms
Abstract Control flow-based feature extraction method has the ability to detect malicious code with higher accuracy than traditional text-based methods. Unfortunately, this method has been encountered with the NP-hard problem, which is infeasible for the large-sized and high-complexity programs. To tackle this, we propose a control flow-based feature extraction dynamic programming algorithm for fast extraction of control flow-based features with polynomial time O($N^{2}$), where N is the number of basic blocks in decompiled executable codes. From the experimental results, it is demonstrated that the proposed algorithm is more efficient and effective in detecting malware than the existing ones. Applying our algorithm to an Internet of Things dataset gives better results on three measures: Accuracy = 99.05%, False Positive Rate = 1.31% and False Negative Rate = 0.66%.
14
Improving support vector machine classifiers by modifying kernel functions
Si Wu · Neural Networks · 1999 · 934 citations
IoTPOT: A Novel Honeypot for Revealing Current IoT Threats
Yin Minn Pa Pa, Shogo Suzuki, Katsunari Yoshioka et al. · Journal of Information Processing · 2016 · 228 citations · Full text