作者: Charles Wheelus , Elias Bou-Harb , Xingquan Zhu
DOI: 10.1109/NTMS.2016.7792484
关键词: Malware 、 Big data 、 Computer security 、 Heterogeneous network 、 Computer science 、 Network security 、 Analytics 、 Data management 、 The Internet 、 Scalability
摘要: Internet and organizational network security is still threatened by devastating malicious activities. Given the continuous escalation of such attacks in terms their frequency, sophistication stealthiness, it paramount importance to generate effective cyber threat intelligence that aim at inferring, attributing, characterizing mitigating misdemeanors. Nevertheless, imperative tasks are partially impeded lack approaches can produce prompt accurate actionable investigating various traffic sources. In this paper, we propose evaluate a big data architecture rooted real-time processing, distributed messaging scalable storage. The key innovation behind proposed automates analysis heterogeneous data, allowing focus remain on devising analytics, rather than being hindered management, aggregation, reconciliation formatting. Empirical evaluations application machine learning analytics exploiting artifacts using 100 GB real traffic, indeed demonstrate practicality, effectiveness, addedvalue architecture.