{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T05:01:18Z","timestamp":1773032478666,"version":"3.50.1"},"reference-count":44,"publisher":"Institution of Engineering and Technology (IET)","issue":"1","license":[{"start":{"date-parts":[[2025,11,7]],"date-time":"2025-11-07T00:00:00Z","timestamp":1762473600000},"content-version":"vor","delay-in-days":310,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62202432"],"award-info":[{"award-number":["62202432"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62272416"],"award-info":[{"award-number":["62272416"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["ietresearch.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["IET Software"],"published-print":{"date-parts":[[2025,1]]},"abstract":"<jats:p>\n                    Ensuring the safety of autonomous driving systems (ADSs) is essential, which requires effective testing methods to enhance system robustness. Fuzz testing (FT) is a widely used technique for uncovering software faults by generating test cases that trigger unexpected system behaviors. However, traditional FT in ADS suffers from significant limitations, including inefficient seed selection, low test case relevance, and inadequate exploration of diverse failure\u2010inducing driving scenarios. Random fuzzing often yields redundant or ineffective cases, limiting the detection of safety\u2010critical issues. To address these challenges, we propose ReinSeed, a reinforcement FT (RFT) framework that integrates three key phases: prefuzzing seed optimization, reinforcement learning (RL)\u2013based scenario generation, and postfuzzing seed prioritization. We introduce a scenario complexity index to prioritize initial seeds before fuzzing. During fuzzing, we model the process as a Markov decision process (MDP) and apply\n                    <jats:italic>Q<\/jats:italic>\n                    \u2010learning to generate scenarios with effective fuzzing action variations guided by driving behaviors, including undesired behaviors and trajectory coverage. To further improve testing effectiveness, we present a postfuzzing prioritization strategy that ranks fuzzed scenarios based on risk energy by incorporating control constraint violation analysis, safety\u2010critical events, and risk\u2010driven trajectory. Experimental results demonstrate that the unified framework\u2014ReinSeed\u2014significantly improves the detection of undesired behaviors, outperforming baseline methods across maps of varying complexity. Furthermore, the multiphase seed optimization showcases distinct contributions of scenario complexity, behavior\u2010guided fuzzing, and risk energy in enhancing both the efficiency and effectiveness of discovering critical behaviors in ADS.\n                  <\/jats:p>","DOI":"10.1049\/sfw2\/8657455","type":"journal-article","created":{"date-parts":[[2025,11,8]],"date-time":"2025-11-08T07:22:29Z","timestamp":1762586549000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["ReinSeed: Reinforcement Fuzz Testing With Multiphase Seed Optimization for Autonomous Driving Systems"],"prefix":"10.1049","volume":"2025","author":[{"given":"Qi","family":"Jin","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3588-7839","authenticated-orcid":false,"given":"Tingting","family":"Wu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9882-9121","authenticated-orcid":false,"given":"Yunwei","family":"Dong","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9671-7836","authenticated-orcid":false,"given":"Zuohua","family":"Ding","sequence":"additional","affiliation":[]},{"given":"Yongkui","family":"Xu","sequence":"additional","affiliation":[]}],"member":"265","published-online":{"date-parts":[[2025,11,7]]},"reference":[{"key":"e_1_2_13_1_2","doi-asserted-by":"crossref","unstructured":"ChengM. ZhouY. andXieX. Behavexplor: Behavior Diversity Guided Testing for Autonomous Driving Systems Proceedings of the 32nd ACM SIGSOFT International Symposium on Software Testing and Analysis (ISSTA) 2023 ACM 488\u2013500.","DOI":"10.1145\/3597926.3598072"},{"key":"e_1_2_13_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/TR.2021.3112538"},{"key":"e_1_2_13_3_2","doi-asserted-by":"crossref","unstructured":"Al SalemH.andSongJ. Grammar-Based Fuzzing Tool Using Markov Chain Model to Generate New Fuzzing Inputs Proceedings of International Conference on Computational Science and Computational Intelligence (CSCI) 2021 IEEE 1924\u20131930.","DOI":"10.1109\/CSCI54926.2021.00358"},{"key":"e_1_2_13_4_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10515-024-00461-w"},{"key":"e_1_2_13_5_2","doi-asserted-by":"crossref","unstructured":"KimS. LiuM. RheeJ. J. JeonY. KwonY. andKimC. H. Drivefuzz: Discovering Autonomous Driving Bugs Through Driving Quality-Guided Fuzzing Proceedings of the 2022 ACM SIGSAC Conference on Computer and Communications Security (CCS) 2022 ACM 1753\u20131767.","DOI":"10.1145\/3548606.3560558"},{"key":"e_1_2_13_6_2","doi-asserted-by":"crossref","unstructured":"PangQ. YuanY. andWangS. Mdpfuzz: Testing Models Solving Markov Decision Processes Proceedings of the 31st ACM SIGSOFT International Symposium on Software Testing and Analysis (ISSTA) 2022 ACM 378\u2013390.","DOI":"10.1145\/3533767.3534388"},{"key":"e_1_2_13_7_2","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0297192"},{"key":"e_1_2_13_8_2","unstructured":"DosovitskiyA. RosG. CodevillaF. LopezA. andKoltunV. CARLA: An Open Urban Driving Simulator Proceedings of the 1st Annual Conference on Robot Learning 2017 PMLR 1\u201316."},{"key":"e_1_2_13_9_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-67361-5_40"},{"key":"e_1_2_13_10_2","doi-asserted-by":"crossref","unstructured":"RongG. ShinB. H. andTabatabaeeH. et al.LGSVL Simulator: A High Fidelity Simulator for Autonomous Driving Proceedings of 23rd International Conference on Intelligent Transportation Systems (ITSC) 2020 IEEE 1\u20136.","DOI":"10.1109\/ITSC45102.2020.9294422"},{"key":"e_1_2_13_11_2","doi-asserted-by":"crossref","unstructured":"HartsellC. RamakrishnaS. DubeyA. StojcsicsD. MahadevanN. andKarsaiG. Resonate: A Runtime Risk Assessment Framework for Autonomous Systems Proceedings of International Symposium on Software Engineering for Adaptive and Self-Managing Systems (SEAMS) 2021 IEEE 118\u2013129.","DOI":"10.1109\/SEAMS51251.2021.00025"},{"key":"e_1_2_13_12_2","doi-asserted-by":"crossref","unstructured":"HofbauerM. KuhnC. B. MengJ. PetrovicG. andSteinbachE. Multi-View Region of Interest Prediction for Autonomous Driving Using Semi-Supervised Labeling Proceedings of the 23rd International Conference on Intelligent Transportation Systems (ITSC) 2020 IEEE 1\u20136.","DOI":"10.1109\/ITSC45102.2020.9294387"},{"key":"e_1_2_13_13_2","doi-asserted-by":"crossref","unstructured":"HofbauerM. KuhnC. B. PetrovicG. andSteinbachE. Telecarla: An Open Source Extension of the Carla Simulator for Teleoperated Driving Research using Off-the-Shelf Components Proceedings of Intelligent Vehicles Symposium (IV) 2020 IEEE 335\u2013340.","DOI":"10.1109\/IV47402.2020.9304676"},{"key":"e_1_2_13_14_2","doi-asserted-by":"crossref","unstructured":"KuhnC. B. HofbauerM. XuZ. PetrovicG. andSteinbachE. Pixel-Wise Failure Prediction for Semantic Video Segmentation Proceedings of International Conference on Image Processing (ICIP) 2021 IEEE 614\u2013618.","DOI":"10.1109\/ICIP42928.2021.9506552"},{"key":"e_1_2_13_15_2","doi-asserted-by":"crossref","unstructured":"RamakrishnaS. LuoB. BarveY. KarsaiG. andDubeyA. Risk-Aware Scene Sampling for Dynamic Assurance of Autonomous Systems Proceedings of International Conference on Assured Autonomy (ICAA) 2022 IEEE 107\u2013116.","DOI":"10.1109\/ICAA52185.2022.00022"},{"key":"e_1_2_13_16_2","unstructured":"VlasicB.andBoudetteN. E. Self-Driving Tesla Involved in Fatal Crash US Says 2016 International New York Times."},{"key":"e_1_2_13_17_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-12388-8_19"},{"key":"e_1_2_13_18_2","doi-asserted-by":"crossref","unstructured":"YangH. ZhouY. andChenT. SimADFuzz: Simulation-Feedback Fuzz Testing for Autonomous Driving Systems 2024 arXiv preprint arXiv: 2412.13802.","DOI":"10.1145\/3744242"},{"key":"e_1_2_13_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2022.3195640"},{"key":"e_1_2_13_20_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-78113-1_11"},{"key":"e_1_2_13_21_2","unstructured":"HuZ. GuoS. ZhongZ. andLiK. Coverage-Based Scene Fuzzing for Virtual Autonomous Driving Testing 2021 arXiv preprint arXiv: 2106.00873."},{"key":"e_1_2_13_22_2","doi-asserted-by":"crossref","unstructured":"SalgadoI. F. QuijanoN. FremontD. J. andCardenasA. A. Fuzzing Malicious Driving Behavior to Find Vulnerabilities in Collision Avoidance Systems Proceedings of IEEE European Symposium on Security and Privacy Workshops (EuroS& PW) 2022 IEEE 368\u2013375.","DOI":"10.1109\/EuroSPW55150.2022.00044"},{"key":"e_1_2_13_23_2","doi-asserted-by":"crossref","unstructured":"WangJ. PunA. andTuJ. et al.AdvSim: Generating Safety-Critical Scenarios for Self-Driving Vehicles Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2021 IEEE 9909\u20139918.","DOI":"10.1109\/CVPR46437.2021.00978"},{"key":"e_1_2_13_24_2","doi-asserted-by":"crossref","unstructured":"BinosiL. RulloL. PolinoM. CarminatiM. andZaneroS. Rainfuzz: Reinforcement-Learning Driven Heat-Maps for Boosting Coverage-Guided Fuzzing Proceedings of the 12th International Conference on Pattern Recognition Applications and Methods (ICPRAM) 2023 SciTePress 39\u201350.","DOI":"10.5220\/0011625300003411"},{"key":"e_1_2_13_25_2","doi-asserted-by":"publisher","DOI":"10.1007\/s38314-019-0155-9"},{"key":"e_1_2_13_26_2","doi-asserted-by":"publisher","DOI":"10.1145\/3512345"},{"key":"e_1_2_13_27_2","unstructured":"MnihV. BadiaA. P. andMirzaM. et al.Asynchronous Methods for Deep Reinforcement Learning Proceedings of International Conference on Machine Learning (ICML) 2016 PMLR 1928\u20131937."},{"key":"e_1_2_13_28_2","unstructured":"LillicrapT. P. HuntJ. J. andPritzelA. et al.Continuous Control With Deep Reinforcement Learning 2015 arXiv preprint arXiv: 1509.02971."},{"key":"e_1_2_13_29_2","doi-asserted-by":"publisher","DOI":"10.3390\/app13042482"},{"key":"e_1_2_13_30_2","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-statistics-031219-041220"},{"key":"e_1_2_13_31_2","doi-asserted-by":"crossref","unstructured":"WangJ. SongC. andYinH. Reinforcement Learning-Based Hierarchical Seed Scheduling for Greybox Fuzzing Proceedings of Network and Distributed System Security Symposium (NDSS) 2021.","DOI":"10.14722\/ndss.2021.24486"},{"key":"e_1_2_13_32_2","doi-asserted-by":"publisher","DOI":"10.3390\/electronics13244962"},{"key":"e_1_2_13_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3233875"},{"key":"e_1_2_13_34_2","doi-asserted-by":"crossref","unstructured":"EomJ. JeongS. andKwonT. CovRL: Fuzzing Javascript Engines With Coverage-Guided Reinforcement Learning for LLM-Based Mutation 2024 arXiv preprint arXiv: 2402.12222.","DOI":"10.1145\/3650212.3680389"},{"key":"e_1_2_13_35_2","doi-asserted-by":"publisher","DOI":"10.1518\/001872006777724417"},{"key":"e_1_2_13_36_2","doi-asserted-by":"crossref","unstructured":"SharifA.andMarijanD. Evaluating the Robustness of Deep Reinforcement Learning for Autonomous Policies in a Multi-Agent Urban Driving Environment 2022 IEEE 22nd International Conference on Software Quality Reliability and Security (QRS) 2022 IEEE 785\u2013796.","DOI":"10.1109\/QRS57517.2022.00084"},{"key":"e_1_2_13_37_2","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2022.3150788"},{"key":"e_1_2_13_38_2","doi-asserted-by":"crossref","unstructured":"LiY. QiH. ZhuF. LvY. andYeP. Interpretable Autonomous Driving Model Based on Cognitive Reinforcement Learning Proceeding of Intelligent Vehicles Symposium (IV) 2024 IEEE 515\u2013520.","DOI":"10.1109\/IV55156.2024.10588661"},{"key":"e_1_2_13_39_2","doi-asserted-by":"publisher","DOI":"10.1145\/3607190"},{"key":"e_1_2_13_40_2","doi-asserted-by":"crossref","unstructured":"HuaiY. ChenY. andAlmaneeS. et al.Doppelg\u00e4nger Test Generation for Revealing Bugs in Autonomous Driving Software Proceedings of IEEE\/ACM 45th International Conference on Software Engineering (ICSE) 2023 IEEE 2591\u20132603.","DOI":"10.1109\/ICSE48619.2023.00216"},{"key":"e_1_2_13_41_2","doi-asserted-by":"crossref","unstructured":"WenC. WangH. andLiY. et al.Memlock: Memory Usage Guided Fuzzing Proceedings of the ACM\/IEEE 42nd International Conference on Software Engineering (ICSE) 2020 IEEE 765\u2013777.","DOI":"10.1145\/3377811.3380396"},{"key":"e_1_2_13_42_2","doi-asserted-by":"crossref","unstructured":"KuuttiS. FallahS. andBowdenR. Training Adversarial Agents to Exploit Weaknesses in Deep Control Policies 2020 IEEE International Conference on Robotics and Automation (ICRA) 2020 IEEE 108\u2013114.","DOI":"10.1109\/ICRA40945.2020.9197351"},{"key":"e_1_2_13_43_2","doi-asserted-by":"publisher","DOI":"10.1145\/3743673"},{"key":"e_1_2_13_44_2","first-page":"128","article-title":"Recent Development and Applications of SUMO-Simulation of Urban Mobility","volume":"5","author":"Krajzewicz D.","year":"2012","journal-title":"International Journal on Advances in Systems and Measurements"}],"container-title":["IET Software"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/pdf\/10.1049\/sfw2\/8657455","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/full-xml\/10.1049\/sfw2\/8657455","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/pdf\/10.1049\/sfw2\/8657455","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T04:09:39Z","timestamp":1773029379000},"score":1,"resource":{"primary":{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/10.1049\/sfw2\/8657455"}},"subtitle":[],"editor":[{"given":"Zahid","family":"Akhtar","sequence":"additional","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2025,1]]},"references-count":44,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2025,1]]}},"alternative-id":["10.1049\/sfw2\/8657455"],"URL":"https:\/\/doi.org\/10.1049\/sfw2\/8657455","archive":["Portico"],"relation":{},"ISSN":["1751-8806","1751-8814"],"issn-type":[{"value":"1751-8806","type":"print"},{"value":"1751-8814","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1]]},"assertion":[{"value":"2025-07-25","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-10-07","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-11-07","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"8657455"}}