SAFLITE: Fuzzing Autonomous Systems via Large Language Models

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Zhu, Taohong, Skapars, Adrians, Mackenzie, Fardeen, Kehoe, Declan, Newton, William, Embury, Suzanne, Sun, Youcheng
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866929648247504896
author Zhu, Taohong
Skapars, Adrians
Mackenzie, Fardeen
Kehoe, Declan
Newton, William
Embury, Suzanne
Sun, Youcheng
author_facet Zhu, Taohong
Skapars, Adrians
Mackenzie, Fardeen
Kehoe, Declan
Newton, William
Embury, Suzanne
Sun, Youcheng
contents Fuzz testing effectively uncovers software vulnerabilities; however, it faces challenges with Autonomous Systems (AS) due to their vast search spaces and complex state spaces, which reflect the unpredictability and complexity of real-world environments. This paper presents a universal framework aimed at improving the efficiency of fuzz testing for AS. At its core is SaFliTe, a predictive component that evaluates whether a test case meets predefined safety criteria. By leveraging the large language model (LLM) with information about the test objective and the AS state, SaFliTe assesses the relevance of each test case. We evaluated SaFliTe by instantiating it with various LLMs, including GPT-3.5, Mistral-7B, and Llama2-7B, and integrating it into four fuzz testing tools: PGFuzz, DeepHyperion-UAV, CAMBA, and TUMB. These tools are designed specifically for testing autonomous drone control systems, such as ArduPilot, PX4, and PX4-Avoidance. The experimental results demonstrate that, compared to PGFuzz, SaFliTe increased the likelihood of selecting operations that triggered bug occurrences in each fuzzing iteration by an average of 93.1\%. Additionally, after integrating SaFliTe, the ability of DeepHyperion-UAV, CAMBA, and TUMB to generate test cases that caused system violations increased by 234.5\%, 33.3\%, and 17.8\%, respectively. The benchmark for this evaluation was sourced from a UAV Testing Competition.
format Preprint
id arxiv_https___arxiv_org_abs_2412_18727
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle SAFLITE: Fuzzing Autonomous Systems via Large Language Models
Zhu, Taohong
Skapars, Adrians
Mackenzie, Fardeen
Kehoe, Declan
Newton, William
Embury, Suzanne
Sun, Youcheng
Software Engineering
Artificial Intelligence
Systems and Control
Fuzz testing effectively uncovers software vulnerabilities; however, it faces challenges with Autonomous Systems (AS) due to their vast search spaces and complex state spaces, which reflect the unpredictability and complexity of real-world environments. This paper presents a universal framework aimed at improving the efficiency of fuzz testing for AS. At its core is SaFliTe, a predictive component that evaluates whether a test case meets predefined safety criteria. By leveraging the large language model (LLM) with information about the test objective and the AS state, SaFliTe assesses the relevance of each test case. We evaluated SaFliTe by instantiating it with various LLMs, including GPT-3.5, Mistral-7B, and Llama2-7B, and integrating it into four fuzz testing tools: PGFuzz, DeepHyperion-UAV, CAMBA, and TUMB. These tools are designed specifically for testing autonomous drone control systems, such as ArduPilot, PX4, and PX4-Avoidance. The experimental results demonstrate that, compared to PGFuzz, SaFliTe increased the likelihood of selecting operations that triggered bug occurrences in each fuzzing iteration by an average of 93.1\%. Additionally, after integrating SaFliTe, the ability of DeepHyperion-UAV, CAMBA, and TUMB to generate test cases that caused system violations increased by 234.5\%, 33.3\%, and 17.8\%, respectively. The benchmark for this evaluation was sourced from a UAV Testing Competition.
title SAFLITE: Fuzzing Autonomous Systems via Large Language Models
topic Software Engineering
Artificial Intelligence
Systems and Control
url https://arxiv.org/abs/2412.18727