2001 · 50 citations · 5 references
ComputingComputer ScienceCybersecurityComputer SecurityData MiningMalware AnalysisEmail SecurityIntrusion DetectionThreat DetectionWindows Malware AnalysisAttachment AnalysisEmail FilteringEmail Malware DetectionMachine Learning Detection ModelsMalicious Script DetectionSecurity AdministratorSpam Detection
We present Malicious Email Filter, MEF, a freely distributed malicious binary filter incorporated into Procmail that can detect malicious Windows attachments by integrating with a UNIX mail server. The system has three capabilities: detection of known and unknown malicious attachments, tracking the propagation of malicious attachments and efficient model update algorithms. The system filters multiple malicious attachments in an email by using detection models obtained from data mining over known malicious attachments. It leverages preliminary research in data mining applied to malicious executables which allows the detection of previously unseen, malicious attachments. In addition, the system provides a method for monitoring and measurement of the spread of malicious attachments. Finally, the system also allows for the efficient propagation of detection models from a central server. These updated models can be downloaded by a system administrator and easily incorporated into the current model. The system will be released under GPL in June 2001.
5
A Study of Cross-Validation and Bootstrap for Accuracy Estimation and Model Selection
Ron Kohavi · 1995 · 10.7K citations · Full text
The MD5 Message-Digest Algorithm
Rivest · Medical Entomology and Zoology · 1992 · 2.9K citations
Data mining methods for detection of new malicious executables
Matthew G. Schultz, Eleazar Eskin, F. Zadok et al. · 2002 · 1.1K citations · Full text