Yusuf Usman

Key Skills

Software

Label Studio

Top Subject Matter

Cybersecurity Domain Expertise

Threat Detection

Healthcare AI

Top Data Types

Text

Document

Top Task Types

Classification

Freelancer Overview

Cybersecurity R&D Engineer (AI Focus) - iSenseHUB. Brings 14+ years of professional experience across complex professional workflows, research, and quality-focused execution. Core strengths include Label Studio, Internal, and Proprietary Tooling. Education includes Master of Science, Quinnipiac University (2023) and Bachelor of Science, ESGT University (2020). AI-training focus includes data types such as Text and labeling workflows including Classification.

Labeling Experience

Cybersecurity R&D Engineer (AI Focus) - iSenseHUB

Label StudioTextClassification

Designed, labeled, and curated datasets for AI-driven cybersecurity threat detection, applying expert knowledge of benign and malicious behavior. Led annotation of authentication event logs to enable identity anomaly detection model training using precise, security-aligned labeling criteria. Conducted quality reviews ensuring HIPAA compliance and regulatory accuracy for healthcare AI data. • Reduced false positive alert rates by 30% in test pipelines • Defined labeling schemas in compliance with NIST/OWASP • Managed data labeling process for healthcare telehealth datasets • Used internal tools and Label Studio for annotation workflow

Designed, labeled, and curated datasets for AI-driven cybersecurity threat detection, applying expert knowledge of benign and malicious behavior. Led annotation of authentication event logs to enable identity anomaly detection model training using precise, security-aligned labeling criteria. Conducted quality reviews ensuring HIPAA compliance and regulatory accuracy for healthcare AI data. • Reduced false positive alert rates by 30% in test pipelines • Defined labeling schemas in compliance with NIST/OWASP • Managed data labeling process for healthcare telehealth datasets • Used internal tools and Label Studio for annotation workflow

2025 - Present

Cybersecurity Incident Response & Business Continuity Intern - Help at Home

TextClassification

Labeled and classified critical vulnerabilities found during enterprise penetration tests using standard risk scoring frameworks. Annotated and maintained enterprise risk register entries, ensuring consistency in taxonomy for vulnerability type, severity, and affected system fields. Supported prioritized security remediation through high-quality annotated data. • Scored vulnerabilities for structured risk analysis • Created and maintained risk register annotations • Informed security response with clear data labeling • Used proprietary and/or internal tools and spreadsheets

Labeled and classified critical vulnerabilities found during enterprise penetration tests using standard risk scoring frameworks. Annotated and maintained enterprise risk register entries, ensuring consistency in taxonomy for vulnerability type, severity, and affected system fields. Supported prioritized security remediation through high-quality annotated data. • Scored vulnerabilities for structured risk analysis • Created and maintained risk register annotations • Informed security response with clear data labeling • Used proprietary and/or internal tools and spreadsheets

2025 - 2025

Cybersecurity Graduate Research Assistant - Quinnipiac University

Label StudioTextClassification

Built and labeled a phishing detection dataset of 120,000+ URLs using multi-class schema (benign, phishing, spam). Defined feature annotation guidelines for network traffic and URL metadata, ensuring consistent and accurate labeling across the research team. Labeled and mapped attack vectors in connected vehicle vulnerability data to MITRE ATT&CK categories for robust threat modeling. • Achieved lower false positives in phishing detection ML tasks • Annotated vulnerability data for structured ML research • Maintained inter-annotator agreement standards • Utilized Label Studio and Python-based workflows

Built and labeled a phishing detection dataset of 120,000+ URLs using multi-class schema (benign, phishing, spam). Defined feature annotation guidelines for network traffic and URL metadata, ensuring consistent and accurate labeling across the research team. Labeled and mapped attack vectors in connected vehicle vulnerability data to MITRE ATT&CK categories for robust threat modeling. • Achieved lower false positives in phishing detection ML tasks • Annotated vulnerability data for structured ML research • Maintained inter-annotator agreement standards • Utilized Label Studio and Python-based workflows

2023 - 2025

Research Assistant - NASA CT Space Grant NextGen AI-Research Lab

TextClassification

Labeled 5G and Massive MIMO wireless network performance and signal data for Deep RL cybersecurity training models. Applied ensemble machine learning feature annotations for advanced phishing attempt datasets contributing to peer-reviewed publications. Distinguished legitimate from adversarial transmissions with precise, domain-specific annotations for physical layer security. • Contributed to improved 5G security and detection accuracy • Supported NASA NextGen AI Research Lab publications • Used proprietary/academic annotation tools in Python • Reduced RL training iteration count by 25%

Labeled 5G and Massive MIMO wireless network performance and signal data for Deep RL cybersecurity training models. Applied ensemble machine learning feature annotations for advanced phishing attempt datasets contributing to peer-reviewed publications. Distinguished legitimate from adversarial transmissions with precise, domain-specific annotations for physical layer security. • Contributed to improved 5G security and detection accuracy • Supported NASA NextGen AI Research Lab publications • Used proprietary/academic annotation tools in Python • Reduced RL training iteration count by 25%

2024 - 2024

Cybersecurity Analyst - National Assembly of Nigeria Senate ICT & Security Unit

TextClassification

Classified and annotated incident and alert data from government information systems using NIST-based risk and threat assessment schemas. Labeled network monitoring alerts during high-stakes operations to separate genuine threats from false positives. Applied structured labeling to support threat pattern analysis and incident response. • Used NIST frameworks for risk scoring annotation • Enabled structured threat intelligence analysis • Supported incident response decision-making • Used internal and custom-developed annotation tools

Classified and annotated incident and alert data from government information systems using NIST-based risk and threat assessment schemas. Labeled network monitoring alerts during high-stakes operations to separate genuine threats from false positives. Applied structured labeling to support threat pattern analysis and incident response. • Used NIST frameworks for risk scoring annotation • Enabled structured threat intelligence analysis • Supported incident response decision-making • Used internal and custom-developed annotation tools

2020 - 2023

Education

Work History