不可信车辆环境中协同异常行为检测的知识迁移
Knowledge Transfer for Collaborative Misbehavior Detection in Untrusted Vehicular Environments
AI总结：
本文针对不可信车辆环境中本地异常行为检测模型易受对抗攻击的问题，提出基于深度强化学习和选择性知识迁移的RSU协同检测方法，在标签翻转和策略诱导攻击下仅从可信源迁移知识，实验证明其能显著缩短训练时间、提升检测性能并增强鲁棒性与泛化能力。
摘要：
车辆移动性凸显了在车辆边缘进行协同异常行为检测的必要性。然而，本地训练的异常行为检测模型容易受到旨在故意影响学习结果的对抗性攻击。在本文中，我们提出了一种基于深度强化学习的方法，该方法利用迁移学习在路侧单元（RSU）之间进行协同异常行为检测。在存在标签翻转和策略诱导攻击的情况下，我们从可信的源RSU中选择性地进行知识迁移，以培养异常行为检测方面的相关专业知识，并避免来自受对手影响的RSU的负面知识共享。我们使用一个开源数据集，在一组多样化的异常行为检测场景上对所提方案的性能进行了评估。实验结果表明，与采用白板学习（tabula rasa learning）的基线方案相比，我们的方法显著缩短了目标RSU的训练时间，并实现了更优的检测性能。通过有效检测此前未见且部分可观测的异常行为攻击，还可以获得增强的鲁棒性和泛化能力。
英文摘要：
Vehicular mobility underscores the need for collaborative misbehavior detection at the vehicular edge. However, locally trained misbehavior detection models are susceptible to adversarial attacks that aim to deliberately influence learning outcomes. In this paper, we introduce a deep reinforcement learning-based approach that employs transfer learning for collaborative misbehavior detection among roadside units (RSUs). In the presence of label-flipping and policy induction attacks, we perform selective knowledge transfer from trustworthy source RSUs to foster relevant expertise in misbehavior detection and avoid negative knowledge sharing from adversary-influenced RSUs. The performance of our proposed scheme is demonstrated with evaluations over a diverse set of misbehavior detection scenarios using an open-source dataset. Experimental results show that our approach significantly reduces the training time at the target RSU and achieves superior detection performance compared to the baseline scheme with tabula rasa learning. Enhanced robustness and generalizability can also be attained, by effectively detecting previously unseen and partially observable misbehavior attacks.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
