SubsidieMeestersPractical, Learning-Based Tools for Finding and Fixing Bugs
BugGPT aims to develop practical AI-based tools for automatically finding and fixing software bugs, enhancing efficiency in the software development process and paving the way for a commercial product.
Projectdetails
Introduction
Software bugs are a major problem for software developers and users alike, as they cause crashes, security vulnerabilities, and data loss. Unfortunately, identifying and fixing software bugs is among the most expensive and time-consuming tasks in software development, accounting for 28% to 50% of the costs of a billion-dollar industry.
Background
The LearnBugs ERC project, on which this proposal is based, has developed ground-breaking techniques to automatically find bugs and propose suitable bug fixes. These techniques are based on artificial intelligence and deep learning, making them particularly powerful for kinds of bugs missed by traditional software developer tools.
Current Status
However, these techniques are currently only available as research prototypes, and there is a gap to be bridged in order to integrate them successfully into the software development workflow.
Project Goals
This Proof of Concept proposal, named BugGPT, aims to make learning-based techniques for finding and fixing software bugs practical and usable by software developers. The project will develop practical tools that enable software developers to automatically find and fix bugs in their code.
Technical Development Activities
To this end, we will perform technical development activities that address the questions of:
- Where to suggest bug fixes
- When to suggest bug fixes
- How to suggest bug fixes
Business Development Activities
Furthermore, we will perform business development activities to:
- Identify potential customers
- Evaluate the usefulness of our tools
- Compare potential business models with each other
Conclusion
Overall, BugGPT has the potential to make a significant impact on the software development industry by making learning-based bug finding and fixing practical for software developers. If successful, the project could be the beginning of a commercial product that stirs up the market of software development tools.
Financiële details & Tijdlijn
Financiële details
| Subsidiebedrag | € 150.000 |
| Totale projectbegroting | € 150.000 |
Tijdlijn
| Startdatum | 1-6-2024 |
| Einddatum | 30-11-2025 |
| Subsidiejaar | 2024 |
Partners & Locaties
Projectpartners
- UNIVERSITY OF STUTTGARTpenvoerder
Land(en)
Vergelijkbare projecten binnen European Research Council
| Project | Regeling | Bedrag | Jaar | Actie |
|---|---|---|---|---|
Change Impact Analysis, Root Cause Analysis, and AI-based Repair for Safe and Secure Software EvolutionFORTE aims to enhance software development by integrating AI for automated code repair and analysis, enabling developers to confidently implement changes without introducing new issues. | ERC Proof of... | € 150.000 | 2024 | Details |
Explore Your Brain 2.0: a maximally effective, usable and scalable growth mindset intervention to break through adolescents’ declining rates of motivation and school achievementsThis project aims to enhance and scale the Explore Your Brain (EYB 2.0) intervention to improve high school students' motivation and resilience through a growth mindset approach. | ERC Proof of... | € 150.000 | 2024 | Details |
Testing Program Analyzers Ad AbsurdumMirandaTesting aims to develop a systematic methodology for testing program analyzers to detect critical bugs, enhancing software reliability in safety-critical applications. | ERC Starting... | € 1.499.991 | 2023 | Details |
A Principled Plan to Prevent Transient Execution AttacksGhostbuster aims to automatically detect and mitigate advanced transient execution attacks by analyzing vulnerable code fragments and modeling attack conditions, enhancing security without crippling performance. | ERC Advanced... | € 2.499.995 | 2025 | Details |
Reactive Synthesis in ActionThe SYNTACT PoC aims to test and promote reactive synthesis technologies in industrial settings to enhance software correctness and reduce development costs, paving the way for broader adoption. | ERC Proof of... | € 150.000 | 2022 | Details |
Change Impact Analysis, Root Cause Analysis, and AI-based Repair for Safe and Secure Software Evolution
FORTE aims to enhance software development by integrating AI for automated code repair and analysis, enabling developers to confidently implement changes without introducing new issues.
Explore Your Brain 2.0: a maximally effective, usable and scalable growth mindset intervention to break through adolescents’ declining rates of motivation and school achievements
This project aims to enhance and scale the Explore Your Brain (EYB 2.0) intervention to improve high school students' motivation and resilience through a growth mindset approach.
Testing Program Analyzers Ad Absurdum
MirandaTesting aims to develop a systematic methodology for testing program analyzers to detect critical bugs, enhancing software reliability in safety-critical applications.
A Principled Plan to Prevent Transient Execution Attacks
Ghostbuster aims to automatically detect and mitigate advanced transient execution attacks by analyzing vulnerable code fragments and modeling attack conditions, enhancing security without crippling performance.
Reactive Synthesis in Action
The SYNTACT PoC aims to test and promote reactive synthesis technologies in industrial settings to enhance software correctness and reduce development costs, paving the way for broader adoption.
Vergelijkbare projecten uit andere regelingen
| Project | Regeling | Bedrag | Jaar | Actie |
|---|---|---|---|---|
Haalbaarheidsonderzoek Learning Journey B&B MarktEduHint ontwikkelt een innovatieve, gepersonaliseerde Learning Journey voor de B2B-markt, gericht op levenslang leren, om de effectiviteit van online training te verbeteren en de haalbaarheid te onderzoeken. | Mkb-innovati... | € 20.000 | 2021 | Details |
Data gedreven schadeanalyse voor de voorspelling van zakelijke elektronica reparatiesHet project onderzoekt de haalbaarheid van een deep learning model voor efficiënte reparaties van zakelijke elektronica binnen Afterservice. | Mkb-innovati... | € 20.000 | 2023 | Details |
AI Fuzzing TechnologieHet project ontwikkelt een geïntegreerde Fuzzing Stack om de beveiliging van embedded software in diverse apparaten te verbeteren, met als doel efficiëntere en veiligere producten te creëren. | Mkb-innovati... | € 208.320 | 2021 | Details |
Optimisation of a novel software tool for automation of the design & verification process of semiconductor developmentLUBIS EDA is developing software to automate chip design and verification, ensuring error-free production, faster market entry, and increased revenue for semiconductor developers. | EIC Accelerator | € 2.499.999 | 2024 | Details |
De optimalisatietool voor machinereparatiesBlue Squid ontwikkelt de SmartFix-app om machinereparaties in de agri- en food-processing sector te optimaliseren met AI en AR, gericht op efficiëntie en kostenbesparing, en onderzoekt de haalbaarheid van uitrol. | Mkb-innovati... | € 19.200 | 2021 | Details |
Haalbaarheidsonderzoek Learning Journey B&B Markt
EduHint ontwikkelt een innovatieve, gepersonaliseerde Learning Journey voor de B2B-markt, gericht op levenslang leren, om de effectiviteit van online training te verbeteren en de haalbaarheid te onderzoeken.
Data gedreven schadeanalyse voor de voorspelling van zakelijke elektronica reparaties
Het project onderzoekt de haalbaarheid van een deep learning model voor efficiënte reparaties van zakelijke elektronica binnen Afterservice.
AI Fuzzing Technologie
Het project ontwikkelt een geïntegreerde Fuzzing Stack om de beveiliging van embedded software in diverse apparaten te verbeteren, met als doel efficiëntere en veiligere producten te creëren.
Optimisation of a novel software tool for automation of the design & verification process of semiconductor development
LUBIS EDA is developing software to automate chip design and verification, ensuring error-free production, faster market entry, and increased revenue for semiconductor developers.
De optimalisatietool voor machinereparaties
Blue Squid ontwikkelt de SmartFix-app om machinereparaties in de agri- en food-processing sector te optimaliseren met AI en AR, gericht op efficiëntie en kostenbesparing, en onderzoekt de haalbaarheid van uitrol.