Download now Free registration required
The volume of malicious software being created at present is so high that it has triggered discussion in the AV industry as to whether a blacklisting model is feasible in the future. In this context, clean data sets are becoming increasingly important and so is the need to classify them. This paper discusses problems and solutions related to gathering and profiling large clean data sets. The paper provides guidelines for gathering clean files and keeping them uncompromised, determining their level of trust and their intrinsic quality (usefulness).
- Format: PDF
- Size: 1662.4 KB