False Positive Reduction
Researching evidence correlation and machine learning for more reliable vulnerability validation.
Cybersecurity • AI • Research
Research
Exploring the intersection of cybersecurity and artificial intelligence, with focus on vulnerability validation, false positive reduction, explainable AI and digital scam detection.
Digital Scam Detection
Applying AI and cybersecurity intelligence to identify suspicious messages, links and documents.
Explainable AI
Exploring transparent risk assessment and understandable security decisions.
Automation
Studying how automation can assist analysts without replacing validation and reasoning.
Research Interests
What I study
Vulnerability Validation
False Positive Reduction
Evidence Correlation
Explainable AI
Security Automation
Machine Learning
Deep Learning
Digital Scam Detection
Bug Bounty Automation
Cybersecurity Education
Current Research
Active research projects
VERA
Vulnerability Evidence Reasoning Architecture is a research project focused on reducing false positives in automated vulnerability detection through evidence correlation, machine learning and continuous learning.
View project →GUARDIAN AI
Artificial intelligence system focused on detecting digital scams by analyzing messages, suspicious URLs, documents, website intelligence and fraud indicators.
View project →Synex
Offensive security platform that supports research into vulnerability validation, security automation, fingerprinting and false positive reduction.
View project →Research Questions
Questions guiding my work
Can evidence correlation reduce false positives without reducing
vulnerability detection capability?
Can artificial intelligence help non-technical users identify digital
scams before interacting with malicious content?
How can security tools explain why a finding is likely valid,
suspicious or false positive?
Can machine learning improve technology fingerprinting and finding
prioritization in bug bounty workflows?
How can vulnerability validation systems learn from analyst feedback
over time?
Methodologies
How I approach research
Cybersecurity Testing
Reconnaissance, vulnerability assessment, controlled labs, validation logic and evidence collection.
Artificial Intelligence
Machine learning, deep learning, transformers, model comparison and explainable AI techniques.
Experimental Evaluation
Dataset generation, controlled environments, baseline comparison and repeatable experiments.
Human Feedback
Analyst validation, feedback loops, learning from previous findings and improving future decisions.
Publications
Articles and papers
No formal publications yet. Current work is focused on the design, development and evaluation of VERA and GUARDIAN AI.
Future publications may include research articles, technical reports, datasets, posters and documentation related to AI-assisted cybersecurity.
Open Problems
Problems I want to explore
How can AI reduce false positives in security scanners?
How can digital scam detection remain explainable?
How can security tools learn from human analysts?
How can evidence be represented for vulnerability reasoning?
How can AI-assisted tools remain useful without creating blind trust?
Research Roadmap
Future direction
2026
├── GUARDIAN AI
├── VERA
├── Scientific competitions
└── Research project development
2027
├── First publications
├── Dataset generation
├── Experimental evaluation
└── Advanced ML research
2028+
├── Explainable Security AI
├── Security Intelligence Systems
├── AI-assisted pentesting
└── Vulnerability reasoning modelsBuilding security tools that reason.
My long-term research goal is to explore how artificial intelligence can support cybersecurity analysis while remaining explainable, responsible and useful for real-world users.
Explore Projects