Data mining methods for detection of new malicious executables

Proceedings of the IEEE Computer Society Symposium on Research in Security and Privacy

Volumn , Issue , 2001, Pages 38-49

  Schultz, Matthew G ^a   Eskin, Eleazar ^a   Zadok, Erez ^b   Stolfo, Salvatore J ^a  

^a Fu Foundation School of Engineering and Applied Science   (United States)

^b Stony Brook University   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

ALGORITHMS; COMPUTER SIMULATION; COMPUTER VIRUSES; CRYPTOGRAPHY; DATA STRUCTURES; ELECTRONIC MAIL; FEATURE EXTRACTION; SECURITY OF DATA;

MALICIOUS EXECUTABLES; TEST SET; TRAINING SET;

DATA MINING;

EID: 0034838197     PISSN: 10637109     EISSN: None     Source Type: Journal    
DOI: None     Document Type: Article

References (27)

1. Automatically generated Win32 heuristic virus detection
2. Learning trees and rules with set-valued features
3. Automated assistance for detecting malicious code
4. Machine learning of rules and trees
5. Protein family classification using sparse Markov transducers
6. Scanners of the year 2000: Heuristics
7. Automatic extraction of computer virus signatures
8. Static analysis virus detection tools for UNIX systems
9. Smooth non-parametric ROC curves for continuous diagnostic tests
10. A study of cross-validation and bootstrap for accuracy estimation and model selection
11. Learning patterns from UNIX processes execution traces for intrusion detection
12. A data mining framework for building intrusion detection models
13. MCF: A malicicus code filter
14. Learning to classify text from labeled and unlabled documents
15. Microsoft hack shows companies are vulnerable
16. Neural networks for computer virus recognition
17. Open problems in computer virus research
18. Anatomy of a commercial-grade immune system