Fraud and abuse detection wired into a SIEM Card-testing and brute-force detection routed to on-c...Fraud and abuse detection wired into a SIEM Card-testing and brute-force detection routed to on-c...
The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Card-testing and brute-force detection routed to on-call with a runbook attached to every alert.
Who it was for: A payments platform exposed to automated card-testing traffic.
The problem. Automated enumeration against payment endpoints is both a fraud loss and an availability threat, and it doesn't announce itself. Without detection it looks like ordinary traffic until the chargebacks arrive.
What I did. Built the log pipeline into the SIEM, then wrote detections for card-testing patterns, brute force and anomalous transaction behaviour. Tuned edge rate-limiting and bot controls to cut volume at the perimeter. Every alert routes to on-call with a runbook attached, so whoever is paged at 3am has the next step in front of them.
The result. Repeat attempts are caught as they start rather than reconstructed afterward, and response is a documented procedure instead of improvisation.
Cybersecurity tools can feel overwhelming for small teams.
Shielda explores a cleaner dashboard experience that helps businesses monitor their digital footprint across domains, email, and social channels.
The interface surfaces password leaks, phishing clones, suspicious mentions, and brand abuse through a clear Security Score, compact threat cards, severity tags, and AI-powered summaries.
Instead of forcing users to interpret complex security data, Shielda helps them understand what happened, how serious it is, and what to do next.
Polar is a local, privacy-focused AI desktop assistant designed around a futuristic HUD interface and system-level interaction.
The project explored how a desktop AI could understand the user's environment, process visual and voice input, and respond or perform actions without relying entirely on cloud services.
Key features:
Local AI assistant architecture
Futuristic Tauri-based desktop HUD
Screen and contextual awareness
OCR-based extraction of text from the screen
Voice interaction pipeline
AI-powered context processing and responses
System-level desktop interaction and automation
Local/offline model execution
Real-time assistant-style interface
OCR pipeline:
Screen capture → OCR → Context extraction → Local AI → Response/Action → HUD
The project combined AI, computer vision, OCR, voice interaction, desktop application development, and modern UI engineering into a single experimental personal-assistant platform.
My contribution: Architecture, application development, AI integration, OCR functionality, UI/HUD development, and system interaction.