Detection of New Malicious Code Using N-grams Signatures.

摘要: Signature-based malicious code detection is the standard technique in all commercial anti-virus software. This method can detect a virus only after has appeared and caused damage. performs poorly when attempting to identify new viruses. Motivated by signature-based for detecting viruses, recent successful text classification method, n-grams analysis, we explore idea of automatically code. We employ analysis generate signatures from benign software collections. The n-gramsbased are capable classifying unseen datasets used large compared earlier applications analysis.