A complete Web3 security toolkit combining AI-powered token auditing, ML-based deployer reputation scoring, and live Etherscan V2 data. Includes static analysis for rugpull detection, RandomForest reputation modeling, contract-fetching automation, and Solidity on-chain registries for transparent, reproducible security insights.

Phoneint-OSINT-Toolkit — a privacy-first phone-number OSINT toolkit (CLI + minimal GUI). Parses and normalizes numbers (E.164), enriches with deterministic metadata, runs optional async adapters (DuckDuckGo, Google, public datasets), computes explainable risk scores and owner intelligence, and exports JSON/CSV/PDF reports.

A customer intelligence engine that predicts subscription probability, models purchase frequency, and computes a unified loyalty risk score. Includes explainability, segment insights, and a scenario simulator, all integrated into an interactive Streamlit dashboard.

AI-powered KYC automation platform with adaptive risk scoring, multi-layer biometrics, OCR, deepfake detection, and cryptographic credentialing. Reduces verification time from 48–72 hours to 8–12 minutes while improving fraud detection to 98.5%.

A multi-agent AI system using Google AI Agent SDK and Gemini to analyze real-time route safety (crime, weather, lighting) and optimize navigation.

CryptGuardian is a research-level concept, created from the perspective of a developer concerned about long-term security for distributed systems. It is not a final product, but an exploration of defense strategies against modern and future threats, including AI-assisted attacks and quantum cryptanalysis.

Phishing detection CLI built on Kali Linux that performs SSL validation, WHOIS analysis, domain heuristics, and weighted risk scoring to classify suspicious URLs.

Streamlit Health Intelligence Platform: digital habits → wellbeing risk scoring, cohort KPIs + 90-day trends, and scenario simulator (synthetic 3,500×24; high_risk_flag).

Actuarial data science project analyzing insurance claims to identify potential fraud and assess customer risk. Includes Python preprocessing, feature engineering, and a stakeholder-ready Tableau dashboard.

OpenSiteTrust is an open, explainable, and reusable website scoring ecosystem

AI-powered corruption detection platform analyzing 3.1M Mexican federal procurement contracts (2002-2025). 16-feature per-sector calibrated risk model with 96% AUC, validated against 15 documented corruption cases worth 253B MXN.

A collection of medical calculations in Python. Example: MELD score for liver disease.

ThreatSentry AI is an intelligent threat hunting dashboard that leverages machine learning to proactively identify and prioritize risks in your network. It automates the process of collecting device information, enriching it with vulnerability data, and assessing risk levels, enabling security teams to focus on the most critical threats.

🛡️ Strengthen Web3 security with our AI-driven token auditor and reputation engine, ensuring safer transactions and reliable smart contracts.

AI-powered behavioural fraud detection system for UPI transactions using FastAPI and Streamlit.

ML-driven authentication orchestration system balancing approval rate, fraud risk and user friction for payment optimization

Supply chain risk & inventory operations — CP-SAT MILP optimization, PPO RL inventory policy, BOM management, supplier risk scoring (rule-based + RF), Clear-to-Build analysis | Enterprise: K8s + Helm + Terraform + MLflow + Prometheus/Grafana | 181 tests

Fintech-based fraud detection system using a weighted ensemble of ML models with Isolation Forest for anomaly detection. Provides real-time risk scoring (0–100) via a Flask API with a React frontend, optimized for high recall and imbalanced financial transaction data.

Python-based enterprise risk intelligence engine for log analysis, anomaly detection, KRI-driven scoring, and automated narrative risk reporting. Designed for SMEs, cybersecurity teams, and governance functions. Built as applied AI technical evidence for the UK Global Talent route. Led by Ibrahim Akinyera.

Full-stack digital payments compliance engine—UPI/RTGS simulator, AML rule engine, ML-based STR detection, SHAP explainability, and audit-ready dashboards.