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

• MyFinancial — Personal Financial Advisor — Financial planning in India is fragmented across banks, insurance, and tax documents.
• PropCheck — AI Property Trust Score for India — Indian property buyers lose lakhs to fraudulent listings on Magicbricks, 99acres, Housing.
• StellarMIND — Chat-to-SQL with RAG — Business users need to query databases without knowing SQL.
• 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.
• 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.
• Agent Autopsy — Forensic Debugger for Failed AI Agent Runs — Most AI agent failures are silent — the run completes, the status code is green, and the result is still wrong.
• tinyvoice — Fine-Tune a Model in Your Own Voice in an Afternoon — Training your own language model sounds like a PhD job that needs a GPU cluster, so most developers never try.
• snap3d — One Photo In, an Editable 3D Model Out — A photo shows you one side of an object; the other five sides are a guess.
• Agentic OS — Force-Directed Map of a 387-Skill Claude Code Setup — An agent setup grows one plugin at a time until it has hundreds of skills, and nobody can see what it actually contains.
• claude-autodev — Autonomous 8-Stage Dev Pipeline for Claude Code — Agentic coding tools stop at a diff.
• KisanSathi — Six AI Farm Experts, Keyless and Local — Farmer-facing AI tools die at the API-key step, answer in English, and hand back generic advice with no live numbers behind it.
• MarginChef — AI Agent That Finds a Restaurant's Margin Leaks — Restaurants run on 3-5% net margins while food costs are up roughly 35% since 2019, and most owners never see per-dish economics.
• Quorum — Deep-Research Agent Swarm with a Shared GraphRAG Brain — Most AI research tools are one model in a loop.
• RegexForge — Plain English to a Regex You Can Trust — Regex is not hard because the syntax is exotic.
• Skillet — Turn Any Docs Page Into an Installable Claude Code Skill — Agent skills are the fastest way to teach a coding agent a new tool, but writing a good SKILL.
• Ladle — Open-Source Prep Forecasting and Food-Cost Leak Detection — Restaurants throw away 4-10% of the food they buy before it reaches a plate, and most owners find out at month end from a food-cost percentage that moved the wrong way, with no idea which ingredient did it.
• Casita — Design Your Home in 3D in the Browser — Home design tools want an install, a login, or a CAD background.
• VoxelForge — A Voxel Sandbox Engine Built Properly — Voxel sandboxes are the demo everyone builds with a coding agent right now, and almost all of them are a throwaway single HTML file that hitches on chunk generation, ships a texture pack, and cannot be read or extended.
• prompt-ocean — Type a Sea, Watch It Exist — Generative interfaces usually hand a model the wheel and hope.
• HEXAPOD — Inverse Kinematics and Gait Simulator — Hexapod gait and leg IK are usually explained with equations and a video, or hidden inside a robotics library.
• avatar-sync — Real-Time Face and Hand Tracking in One HTML File — Face and hand tracking demos come wrapped in a build step, a server, and usually an API key — which puts a wall in front of anyone who just wants to see what the models actually output before building on them.
• TableTalk — Scan, Order, Eat: QR Ordering for Dine-In — Dine-in ordering still means flagging a waiter, squinting at a laminated menu with no photos, and repeating your order across the noise.
• Reliability & Production Readiness — Load testing, observability, and API contracts.
• Open Source Repos — Browse the source code behind these projects.