Javier Yuste

Universidad Rey Juan Carlos
Madrid, Spain

PhD in Artificial Intelligence

Bio

Javier Yuste is an Associate Professor and PhD by the Universidad Rey Juan Carlos, Madrid, where he is part of the Group for Research in Algorithms For Optimization (GRAFO). His research interests focus on the applicability of Artificial Intelligence (AI) techniques to solve Software Engineering problems, particularly in cybersecurity applications.

His research specializes in the intersection between AI techniques and analysis, detection and evasion of malicious software. He has significant experience in vulnerability research, OS internals, malware analysis, incident response operations, SOC analysis and orchestration, and development of internal tools to detect phishing.

Research Focus

Malware Detection and Evasion: His primary research focuses on developing and understanding adversarial examples (AEs) that can evade deep learning-based malware detection systems. He has published notable work on “Optimization of code caves in malware binaries to evade Machine Learning detectors” in Computers & Security journal.

Software Engineering Optimization: He applies metaheuristic algorithms to solve the Software Module Clustering Problem (SMCP), an optimization problem that seeks to maximize the modularity of software projects in the context of Search-Based Software Engineering.

Cybersecurity Applications: His work extends to multi-faceted bypass tactics against static malware detection systems, developing sophisticated methods to understand and counter malware detection through advanced computational techniques.

Metaheuristics and AI: He specializes in applying genetic algorithms and other optimization techniques to solve complex problems in software engineering and cybersecurity domains.

Education

PhD in Artificial Intelligence - Universidad Rey Juan Carlos (2020-present)
Master in Cybersecurity - Universidad Carlos III de Madrid (2019-2020)
Software Engineering - Universidad Politécnica de Madrid (2015-2019)

Key Publications

“Optimization of code caves in malware binaries to evade Machine Learning detectors” - Computers & Security (2022)
“MalwareTotal: Multi-Faceted and Sequence-Aware Bypass Tactics against Static Malware Detection” - IEEE/ACM 46th International Conference on Software Engineering
“An efficient heuristic algorithm for software module clustering optimization” - Research in metaheuristic applications to software engineering

Professional Experience

Cybersecurity Expertise:

Vulnerability research and analysis
Operating systems internals
Malware analysis and incident response operations
SOC analysis and orchestration
Development of internal tools for phishing detection
Source code software vulnerability analysis

Research Activities:

Active presenter at international conferences including Metaheuristic International Conference (MIC)
Collaborative research within the GRAFO group on optimization algorithms
Published research with 77 citations according to Google Scholar

Current Research Projects

Adversarial Machine Learning - Developing evasion techniques for malware detection systems
Software Module Clustering - Optimization approaches for software engineering problems
AI-based Cybersecurity - Advanced computational techniques for security applications