Machine Learning in Security Applications

摘要: One of the most important assets to be protected is information, as every aspect life a society deeply depends on available information. Nowadays, information stored, processed, and communicated by computers. It turns out that computers represent critical tool in modern society. A number protection mechanisms are so far, such antivirus software tools, biometric access control systems. For their effectiveness, frequent updates needed, due rapid evolution attack patterns. In fact, attacks often devised spread running computer programs, which can produce new effective short time frame. machine learning techniques with generalization capability one favorite approaches deploy detection mechanisms. this paper, we discuss should followed when devising for security applications. particular, will focus testing methodologies, performance measures, aimed at reducing intrinsic variability application exhibit real-world scenarios.