ScamRakshak — On-Device AI Scam Detector

Problem

Indians lose thousands of crores annually to digital scams via WhatsApp, SMS, and social media. Existing solutions require internet, collect user data, or lack Indian language support.

Business Impact

Digital scams cost Indians ₹1,750+ crore annually. Victims are often non-technical users who can't evaluate suspicious messages. ScamRakshak gives instant risk scores with Hindi explanations — no internet, no data sharing, no technical knowledge required.

System Approach

• Kotlin + Jetpack Compose with Material 3 for modern Android UI
• 3-tier AI inference: ML Kit Gemma 4 → LiteRT → Rule-based regex (graceful degradation)
• Room database for scam pattern storage and scan history
• CameraX for screenshot capture and OCR-based text extraction
• Hilt for dependency injection across the entire app
• Bilingual output (Hindi + English) for every scam analysis
• Zero network permissions — the app physically cannot send data anywhere

Key Decisions & Trade-offs

• 3-tier fallback over single model — ensures every device gets protection regardless of hardware
• On-device only over cloud AI — privacy is the core promise, not a feature
• Hindi-first over English-only — target users communicate primarily in Hindi and Hinglish
• UPI ID analysis included — UPI scams are the fastest-growing fraud vector in India
• Zero permissions model — builds trust with privacy-conscious users

Current Status

Architecture finalized with 3-tier AI inference engine. Kotlin scaffold with Jetpack Compose, Room, Hilt, and CameraX integration. Rule-based regex engine (Tier 3) operational as universal fallback.

Roadmap

• Integrate ML Kit GenAI with Gemma 4 for on-device LLM analysis
• Add screenshot OCR pipeline with CameraX
• Implement URL safety checker with pattern matching
• Add UPI ID verification against known scam databases
• Launch on Google Play Store

What I'd Improve Next

• Could add community-sourced scam pattern updates via signed JSON bundles
• Consider adding regional language support beyond Hindi (Tamil, Telugu, Marathi)

Explore More

• ClinicAI — WhatsApp AI Clinic Assistant — India has 12 lakh+ small clinics running on phone calls and paper diaries.
• MicroItinerary — AI Travel Planner — Travel apps optimize for proximity and ratings.
• StellarMIND — Chat-to-SQL with RAG — Business users need to query databases without knowing SQL.
• MyFinancial — Personal Financial Advisor — Financial planning in India is fragmented across banks, insurance, and tax documents.
• SanatanApp — Hindu Devotional App — Devotional users in India juggle 5+ separate apps for Chalisa, Gita, Aarti, Ramayan, and Mahabharat.
• SynFlow — Enterprise Intelligence Platform — Private deal networks rely on manual introductions and spreadsheets.
• FinBaby (Jama) — Personal Finance Tracker — Indian middle-class families track expenses across UPI apps, bank statements, and paper notebooks.
• RetailOS — Multi-Tenant Retail SaaS — Indian kirana stores and small retailers use paper registers or basic billing software with no inventory tracking, no GST compliance, and no offline support.
• TripHive — Offline-First Collaborative Trip Planner — Group trip planning is fragmented across WhatsApp, Google Docs, Maps, Splitwise, and email.
• PaisaGuard — Family Budget Survival App — Middle-class families worldwide track expenses inconsistently — UPI apps show transactions but don't enforce budgets.
• rohitraj.tech — Engineering work is often invisible.
• Reliability & Production Readiness — Load testing, observability, and API contracts.
• Open Source Repos — Browse the source code behind these projects.