A Survey of Stealth Malware: Attacks, Mitigation Measures, and Steps Toward Autonomous Open World Solutions

摘要: As our professional, social, and financial existences become increasingly digitized as government, healthcare, military infrastructures rely more on computer technologies, they present larger lucrative targets for malware. Stealth malware in particular poses an increased threat because it is specifically designed to evade detection mechanisms, spreading dormant, the wild extended periods of time, gathering sensitive information or positioning itself a high-impact zero-day attack. Policing growing attack surface requires development efficient anti-malware solutions with improved generalization detect novel types resolve these occurrences little burden human experts possible. In this paper, we survey malicious stealth technologies well existing detecting categorizing countermeasures autonomously. While machine learning offers promising potential autonomous new types, both at network level host level, findings suggest that several flawed assumptions inherent most recognition algorithms prevent direct mapping between problem solution. The notable closed world assumption: no sample belonging class outside static training set will appear query time. We formalized adaptive open framework relate mathematically research from other domains.