文摘
This paper presents a new approach to infer worldwide malware-infected machines by solely analyzing their generated probing activities. In contrary to other adopted methods, the proposed approach does not rely on symptoms of infection to detect compromised machines. This allows the inference of malware infection at very early stages of contamination. The approach aims at detecting whether the machines are infected or not as well as pinpointing the exact malware type/family. The latter insights allow network security operators of diverse organizations, Internet service providers and backbone networks to promptly detect their clients’ compromised machines in addition to effectively providing them with tailored anti-malware/patch solutions. To achieve the intended goals, the proposed approach exploits the darknet Internet space and initially filters out misconfiguration traffic targeting such space using a probabilistic model. Subsequently, the approach employs statistical methods to infer large-scale probing activities as perceived by the dark space. Consequently, such activities are correlated with malware samples by leveraging fuzzy hashing and entropy based techniques. The proposed approach is empirically evaluated using a recent 60 GB of real darknet traffic and 65 thousand real malware samples. The results concur that the rationale of exploiting probing activities for worldwide early malware infection detection is indeed very promising. Further, the results, which were validated using publically available data resources, demonstrate that the extracted inferences exhibit noteworthy accuracy and can generate significant cyber security insights that could be used for effective mitigation.
