Neural Fault Injection: Generating Software Faults from Natural Language
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866916201205071872 |
|---|---|
| author | Cotroneo, Domenico Liguori, Pietro |
| author_facet | Cotroneo, Domenico Liguori, Pietro |
| contents | Traditional software fault injection methods, while foundational, face limitations in adequately representing real-world faults, offering customization, and requiring significant manual effort and expertise. This paper introduces a novel methodology that harnesses the capabilities of Large Language Models (LLMs) augmented with Reinforcement Learning from Human Feedback (RLHF) to overcome these challenges. The usage of RLHF emphasizes an iterative refinement process, allowing testers to provide feedback on generated faults, which is then used to enhance the LLM's fault generation capabilities, ensuring the generation of fault scenarios that closely mirror actual operational risks. This innovative methodology aims to significantly reduce the manual effort involved in crafting fault scenarios as it allows testers to focus on higher-level testing strategies, hence paving the way to new possibilities for enhancing the dependability of software systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_07491 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Neural Fault Injection: Generating Software Faults from Natural Language Cotroneo, Domenico Liguori, Pietro Software Engineering Traditional software fault injection methods, while foundational, face limitations in adequately representing real-world faults, offering customization, and requiring significant manual effort and expertise. This paper introduces a novel methodology that harnesses the capabilities of Large Language Models (LLMs) augmented with Reinforcement Learning from Human Feedback (RLHF) to overcome these challenges. The usage of RLHF emphasizes an iterative refinement process, allowing testers to provide feedback on generated faults, which is then used to enhance the LLM's fault generation capabilities, ensuring the generation of fault scenarios that closely mirror actual operational risks. This innovative methodology aims to significantly reduce the manual effort involved in crafting fault scenarios as it allows testers to focus on higher-level testing strategies, hence paving the way to new possibilities for enhancing the dependability of software systems. |
| title | Neural Fault Injection: Generating Software Faults from Natural Language |
| topic | Software Engineering |
| url | https://arxiv.org/abs/2404.07491 |