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.
Projectdetails
Introduction
Software is the driving force of today's world. Used in almost any system, it has a wide-ranging impact on every area of private and public life, from health to finance, education, entertainment, business, and government.
Challenges in Software Development
Developing software is a cognitively demanding task. Coming up with a software solution for a problem is already challenging, and continuous changes in requirements and in the environment where software is used make it even harder.
As a result, bugs and security vulnerabilities are often introduced during software development. To make things worse, even when these issues are discovered and reported, many of them remain unfixed due to a lack of developer time.
The Promise of Generative AI
Generative AI promises to change the game by being able to automatically repair code. However, it requires developers to validate that the proposed software fixes correctly address the issues, while simultaneously checking that they do not introduce unintended behavior.
FORTE: An AI-Augmented Solution
FORTE combines automated change-impact analysis with automated root cause analysis and AI-based repair to enable an AI-augmented process of developing software.
Our goal with FORTE is to help developers confidently change software without breaking it in unexpected ways, and embrace generative AI to simplify the process of writing and fixing code.
Demonstration of Usefulness
To demonstrate the usefulness of FORTE, we plan to use it with real-world software that is publicly available.
Financiële details & Tijdlijn
Financiële details
Subsidiebedrag | € 150.000 |
Totale projectbegroting | € 150.000 |
Tijdlijn
Startdatum | 1-11-2024 |
Einddatum | 30-4-2026 |
Subsidiejaar | 2024 |
Partners & Locaties
Projectpartners
- IMPERIAL COLLEGE OF SCIENCE TECHNOLOGY AND MEDICINEpenvoerder
Land(en)
Vergelijkbare projecten binnen European Research Council
Project | Regeling | Bedrag | Jaar | Actie |
---|---|---|---|---|
Practical, Learning-Based Tools for Finding and Fixing BugsBugGPT 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. | ERC Proof of... | € 150.000 | 2024 | Details |
Self-Optimizing Static Program AnalysisSOSA aims to revolutionize static program analysis by creating self-adaptive analyses that optimize performance and precision, enhancing software security and developer efficiency. | ERC Advanced... | € 2.500.000 | 2024 | Details |
LEARN: Learning Efficient Automated Reasoning on the NetLEARN automates reasoning and proof strategies for software certification, providing a web-based framework to enhance safety and security in complex computer systems, reducing costs from software errors. | ERC Proof of... | € 150.000 | 2025 | Details |
Resilient and Sustainable Software SecurityThe RS³ project aims to enhance software security by developing resilient and sustainable countermeasures through innovative testing, secure compilers, attack mitigation, and hardware improvements. | ERC Consolid... | € 1.998.851 | 2023 | Details |
Automated Synthesis of Certifiable Control Software for Autonomous VehiclesCertiCar aims to develop a reliable, formally correct advanced collision avoidance system to enhance safety and reduce testing time for autonomous vehicle control software. | ERC Proof of... | € 150.000 | 2024 | Details |
Practical, 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.
Self-Optimizing Static Program Analysis
SOSA aims to revolutionize static program analysis by creating self-adaptive analyses that optimize performance and precision, enhancing software security and developer efficiency.
LEARN: Learning Efficient Automated Reasoning on the Net
LEARN automates reasoning and proof strategies for software certification, providing a web-based framework to enhance safety and security in complex computer systems, reducing costs from software errors.
Resilient and Sustainable Software Security
The RS³ project aims to enhance software security by developing resilient and sustainable countermeasures through innovative testing, secure compilers, attack mitigation, and hardware improvements.
Automated Synthesis of Certifiable Control Software for Autonomous Vehicles
CertiCar aims to develop a reliable, formally correct advanced collision avoidance system to enhance safety and reduce testing time for autonomous vehicle control software.
Vergelijkbare projecten uit andere regelingen
Project | Regeling | Bedrag | Jaar | Actie |
---|---|---|---|---|
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 |
Integrated Safety for Deeply Embedded Systems Software (ISAFE)Het ISAFE-project ontwikkelt een geïntegreerde aanpak voor de kwalificatie van softwaretools in veiligheid kritische systemen, gericht op het voldoen aan veiligheidsstandaarden en het verbeteren van softwareontwikkeling. | Mkb-innovati... | € 160.200 | 2016 | Details |
Haalbaarheidsonderzoek geautomatiseerd proces van code reviewVitas BV onderzoekt de technische en economische haalbaarheid van een AI-gestuurd code review systeem om het ontwikkelproces te versnellen en menselijke fouten te verminderen. | Mkb-innovati... | € 20.000 | 2023 | Details |
Quality Assurance for AIGISKARD is developing an open-source SaaS platform for automated AI quality testing to address ethical biases and prediction errors, aiming to lead in compliance with the EU AI Act. | EIC Accelerator | € 2.499.999 | 2023 | Details |
A metapredictive model of synthetic awareness for enabling tool inventionMETATOOL aims to develop a computational model of synthetic awareness in robots to enable self-evaluation and tool invention, advancing adaptive AI technology. | EIC Pathfinder | € 3.298.843 | 2022 | Details |
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.
Integrated Safety for Deeply Embedded Systems Software (ISAFE)
Het ISAFE-project ontwikkelt een geïntegreerde aanpak voor de kwalificatie van softwaretools in veiligheid kritische systemen, gericht op het voldoen aan veiligheidsstandaarden en het verbeteren van softwareontwikkeling.
Haalbaarheidsonderzoek geautomatiseerd proces van code review
Vitas BV onderzoekt de technische en economische haalbaarheid van een AI-gestuurd code review systeem om het ontwikkelproces te versnellen en menselijke fouten te verminderen.
Quality Assurance for AI
GISKARD is developing an open-source SaaS platform for automated AI quality testing to address ethical biases and prediction errors, aiming to lead in compliance with the EU AI Act.
A metapredictive model of synthetic awareness for enabling tool invention
METATOOL aims to develop a computational model of synthetic awareness in robots to enable self-evaluation and tool invention, advancing adaptive AI technology.