crit finds@critfinds

AproxResearch is a full-stack AI security research platform built to accelerate Web3 vulnerability discovery and validation. The backend powers an exploit-intelligence pipeline that ingests smart contracts, analyzes control flow and state transitions, and maps findings against known exploit classes such as access-control bypass, token/accounting mismatch, and economic attack surfaces. The frontend at aproxresearch.org provides an interactive workspace where researchers can review AI-generated findings, track severity, and organize manual validation notes. What makes the project practical is the focus on analyst workflow: the system does not stop at generic “possible issue” outputs. It structures findings with reproducible context, highlights likely impact paths, and supports evidence-driven triage so security reviewers can move faster from detection to validation. The platform is designed for both individual researchers and teams who need consistent, explainable, and auditable vulnerability research. Our goal is to reduce time-to-insight in smart contract audits while improving quality and repeatability, combining AI-assisted detection with human expert verification for real-world exploit research.

Grab your ideas, spin up compute, and start building what’s next! Start with $100 in AMD Developer Cloud credits and begin building right away. Get access to hands-on tutorials, workshops, and curated learning resources to help you build faster and go further. To unlock credits and join the hackathon, sign up for the AMD AI Developer Program. 🤝 Go solo or team up — ship something real. 💰 $21,500+ total prize pool & 1 × AMD Radeon™ AI PRO R9700 GPU up for grabs. 📍 On-site Venue (May 9-10): MindsDB SF AI Collective 3154 17th St, San Francisco, California, USA 📍On-site participation is by invitation only. Travel and accommodation expenses will not be covered. 🧑‍💻 Developers, builders, and innovators - bring your boldest ideas and let’s turn them into real AI systems on AMD.