sai charan@saicharanbalina2391797

Modern applications depend on authorization rules to decide who can access, modify, export, or delete resources. A small code or policy change can silently change these decisions while conventional tests remain green. This creates a difficult developer problem: manually validating combinations of roles, resources, actions, ownership, tenant boundaries, and account states is time-consuming and easy to miss. PermitProof is a deterministic authorization regression-testing tool that helps developers verify security-sensitive changes before release. The user loads a baseline authorization implementation and a proposed candidate version. PermitProof evaluates a synthetic scenario matrix covering roles, resources, actions, ownership, tenant relationships, and user states. It then compares the authorization decisions between the two versions and identifies meaningful changes such as unexpected access grants, revoked permissions, privilege escalation, ownership bypass, and tenant-isolation failures. Instead of producing only a generic security score, PermitProof shows the exact scenario where behavior changed. For each important finding, the user can inspect the baseline decision, candidate decision, affected role/resource/action combination, and supporting evidence. PermitProof also provides a minimal-counterexample workflow that reduces a complex failing scenario to the smallest set of conditions required to reproduce the authorization regression. From that counterexample, the system generates a focused regression test that developers can copy into their test suite. The final step is an Authorization Change Certificate containing the verification run, scenario counts, detected changes, critical findings, counterexamples, and generated tests. The certificate uses deterministic verification logic rather than relying on an AI model to decide whether the change is safe. The target users are software developers, security engineers, QA engineers, and reviewers responsible for authorization-sensitive applications. What makes PermitProof different is its evidence-first workflow: Authorization Change → Scenario Matrix → Baseline vs Candidate → Access Delta → Minimal Counterexample → Regression Test → Change Certificate. The project uses a fully synthetic dataset so the demonstration is reproducible without personal, client, or confidential data. It is designed as a static web application that can be demonstrated immediately in the browser and deployed through GitHub Pages.

CyberVoice AI is a real-time voice-based cybersecurity assistant designed to help users identify and report suspicious emails through natural voice conversations. Built using AssemblyAI's voice AI technology, the application allows users to describe potential phishing incidents, answer contextual follow-up questions, and receive understandable security guidance. The agent uses conversational context to collect incident details such as the type of suspicious message, whether a link was clicked, and whether credentials may have been shared. It converts relevant information into a structured incident report that users can review and confirm before saving. The application combines a voice interaction interface with a FastAPI backend and a React-based dashboard. The backend manages incident data, validates structured inputs, and provides reporting functionality. The dashboard displays conversation transcripts, incident details, and report status. CyberVoice AI focuses on making cybersecurity reporting more accessible through voice while maintaining transparency about uncertain information. The prototype uses controlled test scenarios and simulated incident data to demonstrate the workflow safely. The project showcases real-time voice interaction, AI-assisted information extraction, backend tool integration, and a practical cybersecurity use case powered by AssemblyAI.

Six Matches. One leaderboard. Build on AMD, earn points and compete for prizes.

🌎 Online Hackathon | 💻 Online Build: Sept 26 - Oct 5, 2026 A virtual, global hackathon. Build from anywhere in the world. Dark Factory is the official hackathon of WeAreDevelopers World Congress North America, presented by BAND, but you don't need to be in San Jose to take part. For one week, you build a software factory in BAND Desktop: a band of coding agents that plans work, implements it and checks its own results. 🎟️ Bonus for sign-ups: you are eligible for a free ticket to WeAreDevelopers World Congress North America in San Jose (Sep 23–25). If you do go, stop by the BAND booth: a surprise is waiting for you.

💻 Online Hackathon | ⏳ Build: 48 hours | 📅 September 25–27, 2026 The official IBM Bob 2.0 hackathon. Build what's next in AI-assisted development, alongside the developers and experts shaping it. ⭐ Get help from experts throughout the event 🤝 Join a team or build solo 💰 Prize pool: $12,000 🧑🏻‍💻 Register before the Kick-Off Stream to start building with Bob

🌎 Online Hackathon | 💻 Month-long challenge | Dates: Sep 1–30, 2026 | 🏆 $10,000 Prize Pool ($5k cash + $5k in AAI credits) A month-long online challenge run by lablab.ai together with AssemblyAI, the Voice AI infrastructure company for builders. Every participant builds on AssemblyAI. You can join at any point — registration stays open for the whole build window, so you can start on day one or pick the project up halfway through and still submit. 🌍 Fully online hackathon. Join and build from anywhere in the world.