Advanced malicious beaconing detection through AI. Issue 3 (March 2020)

• Record Type: Journal Article
• Authors: Borchani, Yessine
• Is Part Of: Network security. Volume 2020:Issue 3(2020)
• Page Start: 8
• Page End: 14
• Publication Date: 2020-03
• Subjects: Computer security -- Periodicals; Computer networks -- Security measures -- Periodicals; Electronic data processing departments -- Security measures -- Periodicals; Computers -- Access control -- Periodicals; 005.805
• DOI: 10.1016/S1353-4858(20)30030-1
• Languages: English
• ISSNs: 1353-4858

Abstract

Abstract : As efforts to more securely protect the world's privacy and data continue to improve, with the introduction of stricter compliance regulations and the deployment of increasingly complex network infrastructures, so too has enterprise adoption of and reliance on encryption. Cryptographic encryption protocols, namely secure sockets layer (SSL) and its successor, transport layer security (TLS), were estimated by Gartner to be implemented across 80% of enterprise web traffic in 2019, and the Ponemon Institute found that 43% of organisations had a consistent, enterprise-wide encryption strategy in place in 2018. 1, 2 As efforts to more securely protect the world's privacy and data continue to improve, so too has enterprise adoption of and reliance on encryption. However, threat actors have also started to leverage encryption and are hiding their nefarious activities among regular encrypted traffic, making malicious packets nearly impossible to detect. Fortunately, by using AI, enterprises can achieve a quicker and more accurate analysis of all traffic on their network to check for beaconing behaviour, explains Yessine Borchani of Barac.