Enhancing Continual Learning for Software Vulnerability Prediction: Addressing Catastrophic Forgetting via Hybrid-Confidence-Aware Selective Replay for Temporal LLM Fine-Tuning
增强软件漏洞预测的持续学习:通过混合-置信度感知选择性重放应对灾难性遗忘
机构 * School of Computer Science, University of Nottingham, Nottingham, United Kingdom(诺丁汉大学计算机科学学院) ; School of Informatics and Computing, Northern Arizona University, Flagstaff, United States of America(北亚利桑那大学信息学院) ; School of Computer Science, University of Nottingham, Ningbo, China(诺丁汉大学宁波校区)
专题命中 指令微调 :LLM(title,abstract);large language model(abstract);language model(abstract);分类 cs.AI、cs.LG
AI总结 本文提出Hybrid-CASR方法,通过置信度感知和类平衡的选性重放,提升LLM在时间漂移下的漏洞检测准确率和效率。
Comments Accepted for publication in the Proceedings of the 2026 International Conference on Information Systems Security and Privacy (ICISSP)
Journal ref Proceedings of the 12th International Conference on Information Systems Security and Privacy - Volume 1, ISBN 978-989-758-800-6, ISSN 2184-4356, pages 474-485, 2026