Automated Evolution of the Softwares Robustness through Patternizing Attack and defend Semantic Stru
Abstract
Several evidence indicates that malicious cyber actors learn, adapt, or, in other words, react to the defensive measures put into pl,ace by the cybersecurity community, as much as network defenders react to attacks. Therefore, in the domain of cybersecurity, the pa,tterns of co-evolution appear between the cyber attacker and defender as attack-and-defend adaptations. In this regard, we propose t,o study and exploit this forms of co-evolution between cybersecurity attacks and defends to enable defenders to strategically positi,on themselves ahead of cyber threats. To this end, this research constitutes a paradigm shift in the development of automated and de,fensive evolutionary techniques between pairs of software artifacts in response to the malicious attacks. To achieve the goal of sof,twares evolutionary robustness, this work brings expertise from the domains of software engineering, machine learning, and deep lea,rning to develop novel approaches to incrementally infer patterns of co-evolution between software artifacts within the existing sof,tware systems. Patternizing the co-evolution, the proposed approach further leverages this information to automatically apply remedi,ation to the existing software artifacts after a particular change occurred.
Document Details
- Document Type
- DoD Grant Award
- Publication Date
- Jul 13, 2022
- Source ID
- N000142212553
Entities
People
- Mona Rahimi
Organizations
- Northern Illinois University
- Office of Naval Research
- United States Navy