Neural Fault Injection: Generating Software Faults from Natural Language

2024/04/11 by Domenico Cotroneo, Cotroneo, Domenico, Pietro Liguori +1 · 1 citation
Computer Science · #FOS: Computer and information sciences #Software Engineering (cs.SE) #Software Engineering Research #Software Reliability and Analysis Research #Software Testing and Debugging Techniques

paper · pdf · doi:10.48550/arxiv.2404.07491

openalex publication_date 2024/04/11 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

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.

Cited by

• LLMs-Powered Real-Time Fault Injection: An Approach Toward Intelligent Fault Test Cases Generation

Related

• A Survey on Failure Analysis and Fault Injection in AI Systems
• Large-Scale Application of Fault Injection into PyTorch Models -- an Extension to PyTorchFI for Validation Efficiency
• Fault injection for the masses
• On Human Intellect and Machine Failures: Troubleshooting Integrative Machine Learning Systems
• Faults in Deep Reinforcement Learning Programs: A Taxonomy and A Detection Approach