Feature graph construction with static features for malware detection

arXiv:2404.16362v1 Announce Type: new
Abstract: Malware can greatly compromise the integrity and trustworthiness of information and is in a constant state of evolution. Existing feature fusion-based detection methods generally overlook the correlation between features. And mere concatenation of features will reduce the model's characterization ability, lead to low detection accuracy. Moreover, these methods are susceptible to concept drift and significant degradation of the model. To address those challenges, we introduce a feature graph-based malware detection method, MFGraph, to characterize applications …

accuracy arxiv can compromise construction correlation cs.cr detection evolution feature features fusion graph information integrity low malware malware detection state trustworthiness