AI Web Application Firewall

AI-WAF (Artificial Intelligence Web Application Firewall) is a full-stack security application designed to safeguard AI systems and web applications from malicious user inputs. The system uses an AI model to analyze incoming prompts and classify them as Benign, Suspicious, or Malicious, assigning a dynamic risk score and an explanation for each decision. The backend is built using FastAPI and integrates with an AI inference model via Groq, enabling fast, real-time intent analysis. A secure API endpoint processes user input and returns structured security insights, ensuring consistent and safe responses even in failure scenarios. The frontend is developed with HTML, CSS, and JavaScript, providing a responsive and user-friendly interface where users can test prompts and instantly view security assessments. The frontend and backend are deployed independently using Netlify and Railway, following modern microservice deployment practices. AI-WAF is capable of detecting: Prompt injection attempts SQL injection-like patterns Cross-site scripting (XSS) payloads Data exfiltration and policy-bypass attempts This project demonstrates real-world implementation of AI security, API design, cloud deployment, and frontend-backend integration, making it suitable for production demos, hackathons, and portfolio showcases.