VeriBee

Verification and AI for identifying and repairing security vulnerabilities in source code.

Year

8

Project

VeriBee

University

University of Manchester

URL

veribee.co

Share this project

Market Need

Manual testing of software is impractical due to high costs, complexity, and a shortage of skilled testers. Existing automated tools often fail to identify or fix security issues and can generate many false alarms, creating additional challenges for developers. There is a pressing need for powerful and reliable testing tools to prevent cyber-attacks, especially in high-stakes industries.

Solution

VeriBee combines advanced verification and AI methods to detect and fix over 40 types of security vulnerabilities in C language source code (can be extended to other languages), while keeping false positives at a minimum. The containerised product can easily be integrated into a company’s existing technology stack, can run on the cloud or locally, and generates detailed bug reports with locations, types, and suggested fixes, enhancing security and reliability, and enabling continuous learning of software developers. This has earned the solution 18 awards in international software testing competitions.

Target Market

  • C/C++ software testing segment targeting security-conscious companies focused on low-level system development including firmware, device drivers, compilers, and operating systems.

Status

  • Proof of concept and testing complete.
  • In discussions with possible early adopters.

Needs

  • Investment to develop proof of concept into a minimum viable product.
  • To extend solution to multi-language support.
Close

Connect with Innovate UK Business Connect

Join Innovate UK Business Connect's mailing list to receive updates on funding opportunities, events and to access Innovate UK Business Connect's deep expertise. Please check your email to confirm your subscription and select your area(s) of interest.