LLMs-Powered Real-Time Fault Injection: An Approach Toward Intelligent Fault Test Cases Generation
- URL: http://arxiv.org/abs/2511.19132v1
- Date: Mon, 24 Nov 2025 13:57:31 GMT
- Title: LLMs-Powered Real-Time Fault Injection: An Approach Toward Intelligent Fault Test Cases Generation
- Authors: Mohammad Abboush, Ahmad Hatahet, Andreas Rausch,
- Abstract summary: A novel Large Language Models (LLMs)-assisted fault test cases (TCs) generation approach is proposed in this paper.<n>The proposed approach exhibits high performance in terms of FSRs classification and fault TCs generation with F1-score of 88% and 97.5%, respectively.
- Score: 1.9435397960631864
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: A well-known testing method for the safety evaluation and real-time validation of automotive software systems (ASSs) is Fault Injection (FI). In accordance with the ISO 26262 standard, the faults are introduced artificially for the purpose of analyzing the safety properties and verifying the safety mechanisms during the development phase. However, the current FI method and tools have a significant limitation in that they require manual identification of FI attributes, including fault type, location and time. The more complex the system, the more expensive, time-consuming and labour-intensive the process. To address the aforementioned challenge, a novel Large Language Models (LLMs)-assisted fault test cases (TCs) generation approach for utilization during real-time FI tests is proposed in this paper. To this end, considering the representativeness and coverage criteria, the applicability of various LLMs to create fault TCs from the functional safety requirements (FSRs) has been investigated. Through the validation results of LLMs, the superiority of the proposed approach utilizing gpt-4o in comparison to other state-of-the-art models has been demonstrated. Specifically, the proposed approach exhibits high performance in terms of FSRs classification and fault TCs generation with F1-score of 88% and 97.5%, respectively. To illustrate the proposed approach, the generated fault TCs were executed in real time on a hardware-in-the-loop system, where a high-fidelity automotive system model served as a case study. This novel approach offers a means of optimizing the real-time testing process, thereby reducing costs while simultaneously enhancing the safety properties of complex safety-critical ASSs.
Related papers
- CARE: Decoding Time Safety Alignment via Rollback and Introspection Intervention [68.95008546581339]
Existing decoding-time interventions, such as Contrastive Decoding, often force a severe trade-off between safety and response quality.<n>We propose CARE, a novel framework for decoding-time safety alignment that integrates three key components.<n>The framework achieves a superior balance of safety, quality, and efficiency, attaining a low harmful response rate and minimal disruption to the user experience.
arXiv Detail & Related papers (2025-09-01T04:50:02Z) - Training Language Models to Generate Quality Code with Program Analysis Feedback [66.0854002147103]
Code generation with large language models (LLMs) is increasingly adopted in production but fails to ensure code quality.<n>We propose REAL, a reinforcement learning framework that incentivizes LLMs to generate production-quality code.
arXiv Detail & Related papers (2025-05-28T17:57:47Z) - Advancing Embodied Agent Security: From Safety Benchmarks to Input Moderation [52.83870601473094]
Embodied agents exhibit immense potential across a multitude of domains.<n>Existing research predominantly concentrates on the security of general large language models.<n>This paper introduces a novel input moderation framework, meticulously designed to safeguard embodied agents.
arXiv Detail & Related papers (2025-04-22T08:34:35Z) - Safety-Driven Deep Reinforcement Learning Framework for Cobots: A Sim2Real Approach [1.0488553716155147]
This study presents a novel methodology incorporating safety constraints into a robotic simulation during the training of deep reinforcement learning (DRL)
The framework integrates specific parts of the safety requirements, such as velocity constraints, directly within the DRL model.
The proposed approach outperforms the conventional method by a 16.5% average success rate on the tested scenarios.
arXiv Detail & Related papers (2024-07-02T12:56:17Z) - Towards a Framework for Deep Learning Certification in Safety-Critical Applications Using Inherently Safe Design and Run-Time Error Detection [0.0]
We consider real-world problems arising in aviation and other safety-critical areas, and investigate their requirements for a certified model.
We establish a new framework towards deep learning certification based on (i) inherently safe design, and (ii) run-time error detection.
arXiv Detail & Related papers (2024-03-12T11:38:45Z) - Analyzing Adversarial Inputs in Deep Reinforcement Learning [53.3760591018817]
We present a comprehensive analysis of the characterization of adversarial inputs, through the lens of formal verification.
We introduce a novel metric, the Adversarial Rate, to classify models based on their susceptibility to such perturbations.
Our analysis empirically demonstrates how adversarial inputs can affect the safety of a given DRL system with respect to such perturbations.
arXiv Detail & Related papers (2024-02-07T21:58:40Z) - STEAM & MoSAFE: SOTIF Error-and-Failure Model & Analysis for AI-Enabled
Driving Automation [4.820785104084241]
This paper defines the SOTIF Temporal Error and Failure Model (STEAM) as a refinement of the SOTIF cause-and-effect model.
Second, this paper proposes the Model-based SOTIF Analysis of Failures and Errors (MoSAFE) method, which allows instantiating STEAM based on system-design models.
arXiv Detail & Related papers (2023-12-15T06:34:35Z) - Evaluating Model-free Reinforcement Learning toward Safety-critical
Tasks [70.76757529955577]
This paper revisits prior work in this scope from the perspective of state-wise safe RL.
We propose Unrolling Safety Layer (USL), a joint method that combines safety optimization and safety projection.
To facilitate further research in this area, we reproduce related algorithms in a unified pipeline and incorporate them into SafeRL-Kit.
arXiv Detail & Related papers (2022-12-12T06:30:17Z) - Efficient falsification approach for autonomous vehicle validation using
a parameter optimisation technique based on reinforcement learning [6.198523595657983]
The widescale deployment of Autonomous Vehicles (AV) appears to be imminent despite many safety challenges that are yet to be resolved.
The uncertainties in the behaviour of the traffic participants and the dynamic world cause reactions in advanced autonomous systems.
This paper presents an efficient falsification method to evaluate the System Under Test.
arXiv Detail & Related papers (2020-11-16T02:56:13Z) - Evaluating the Safety of Deep Reinforcement Learning Models using
Semi-Formal Verification [81.32981236437395]
We present a semi-formal verification approach for decision-making tasks based on interval analysis.
Our method obtains comparable results over standard benchmarks with respect to formal verifiers.
Our approach allows to efficiently evaluate safety properties for decision-making models in practical applications.
arXiv Detail & Related papers (2020-10-19T11:18:06Z) - Efficient statistical validation with edge cases to evaluate Highly
Automated Vehicles [6.198523595657983]
The widescale deployment of Autonomous Vehicles seems to be imminent despite many safety challenges that are yet to be resolved.
Existing standards focus on deterministic processes where the validation requires only a set of test cases that cover the requirements.
This paper presents a new approach to compute the statistical characteristics of a system's behaviour by biasing automatically generated test cases towards the worst case scenarios.
arXiv Detail & Related papers (2020-03-04T04:35:22Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.