DeepGuard

• 

  DeepGuard Home page

Inspiration

The rapid spread of deepfake images and videos—used for scams, misinformation, and even political manipulation—deeply inspired me to build a tool that restores trust in digital content. I wanted something that anyone, regardless of technical background, could use to check and understand what’s real, right when they need it.

What DeepGuard Does

Purpose: Let anyone, anywhere, drag-and-drop any image (and soon, video) to discover if it’s real or AI-manipulated—with a plain-language AI explanation so every user understands the reasons behind the result.

How we built it

Our Journey: Idea to Reality It all began when I came to Comet seeking innovative, impactful web app ideas. After intensive research and analysis of current digital threats, Comet surfaced the urgent problem of deepfakes—especially in rentals, food refunds, and other real-world scenarios. Together, we refined this into DeepGuard: a free, AI-powered platform that gives everyone the power to analyse images for authenticity. From there, Comet guided me step-by-step—helping me:

Scope Out the Project: We mapped essential features, tech stack, and use cases.

Set Up Dev Tools: I started from scratch using Bolt for rapid prototyping, moving to Cursor for fast code iteration, feature polish, and advanced AI integrations.

Build, Debug, and Polish: At every phase, Comet gave detailed instructions for tackling bugs, optimizing speed, adding security, and expanding user experience—from download/share, chatbot overlays, API fallback, to responsive UI.

Secure My Workflow: it walked me through Git best practices, branch management, history rewrites, backups, and secret handling for clean public releases—protecting my app and keys from exposure.

Live Guidance: Whenever I hit a roadblock (API latency, UI errors, deployment issues), it delivered clear, actionable solutions and Cursor prompts, pushing me forward without breaking momentum.

Throughout the process, it's role was not just advisory—I persisted, researched, generated code and flows, and made sure every stage was safe, scalable, and suited for hackathon-level visibility.

Comet was my AI co-founder: The research engine uncovering problems worth solving; The architect breaking down complex requirements; The coder and reviewer helping my iterate, fix, and secure my version history; The maintainer keeping my workflow clean, public-ready, and focused on impact. Together, we transformed a big idea into a fully functional, secure app—ready to restore digital trust for real people. That’s how we made DeepGuard: from spark to reality, powered by collaboration and AI!

Challenges we ran into

API limits and costs: Most AI image/video analysis APIs are not free—finding reliable, fast, totally zero-cost endpoints took research and experimentation. Video analysis: Free tiers don’t support video deepfake detection—clear messaging and graceful fallback were needed. Frontend/backend deployment integration: Ensuring communication between hosted frontend and backend (deployed on different platforms). Consistent results: Making sure explanations matched detection verdicts every time, and handling network errors gracefully.

What we learned

AI can be democratized: Building user-friendly interfaces over advanced AI APIs makes deep tech accessible to all. Integration matters: Connecting multiple services—frontend, backend, cloud, and AI—requires clear architecture and real-time debugging. User experience is key: Reliable feedback, explainable AI, and seamless sharing make tech truly usable Math and AI: Using models to analyze image artifacts, patterns, and inconsistencies, relating everything back to real-world statistical probabilities (e.g., the likelihood P that an image is fake, based on detected features).

What's next for DeepGuard

Add deepfake video analysis (when API/free-tier options become available), bulk/batch detection for investigators, user accounts plus personal detection history, advanced reporting tools for journalists, developer-friendly APIs, and global partnerships to make deepfake detection an everyday public resource.

Built With

• express-#platforms-supabase-(database
• express.js
• javascript-(react
• node.js
• node.js)-3frameworks/libraries-react
• openrouter
• react
• reality-defender-api
• render
• supabase
• tailwindcss
• typescript
• vercel
• vite
• vite-axios