论文提出 Sybil-TraceGuard，利用动态时空图神经网络在半监督条件下把不断切换的车辆伪名追溯到攻击者。框架包含流式攻击预筛查、动态图构建、空间图注意力编码，以及多尺度时序审计，并以 Mean-Teacher 方式训练。

Connected and autonomous vehicles (CA Vs) face severe Sybil attacks, where attackers exploit privacy-preserving pseudonym-switching mechanisms to anomaly alternate identities while forging Basic Safety Messages (BSMs). Although existing schemes can flag suspicious behaviors, these temporally fragmented Sybil identities render traditional single-point and sequence-based deep learning methods ineffective. Linking these fragmented identities back to the source attacker is essential for root-cause elimination, particularly under extreme label scarcity. Therefore, the Sybil-TraceGuard is proposed as a dynamic semisupervised spatio-temporal GNN framework for Sybil Guardian, prioritizing “who is responsible” over “whether an attack is happening”. It comprises four tightly coupled modules: Incremental Stream Attack Detection (ISAD) for efficient Sybil attack pre-screening; the Dynamic Topology-aware Constructor (DTC) for constructing spatio-temporal dynamic graphs; the Spatial GAT-Encoder with Multi-head Attention (SGEM) to capture multi-identity logical conflicts in spatial interactions; and the Multi-scale Spatio-Temporal Audit (MSTA) to audit shortterm and long-term temporal inconsistencies. These modules are optimized within a semi-supervised Mean-Teacher framework via feature-edge shuffling perturbations, regularizing the latent feature space using minimal labels. Experiments across four Sybil attack scenarios demonstrate that Sybil-TraceGuard effectively links fragmented pseudonyms to source attackers. It outperforms state-of-the-art baselines across unlabeled ratios of 0.70–0.95, maintaining high stability and sensitivity despite extreme class imbalance and varying hyperparameter settings.

车辆为保护隐私会切换伪名，Sybil 攻击者还能伪造基本安全消息；传统检测只判断是否有攻击，难以把被切碎的身份关联回同一攻击源，尤其在标注很少时。

To address these challenges, we propose Sybil-TraceGuard, traceability-enhancedSybil Guardian for CA Vs using semisupervised dynamic GNN.

研究目标从检测“是否发生攻击”推进到追溯“谁在负责”，并用动态空间交互与短、长时序一致性联合关联多个伪名。

Application-layer BSM evidence is exploited to associate fragmented pseudonyms through progressive behavioral consistency auditing. •Dynamic spatio-temporal GNN representation.We propose a more discriminative feature space and a collaborative framework comprising four specialized modules.

先用增量流式检测预筛查，再构建动态时空图；空间 GAT 捕捉不同伪名间的逻辑冲突，多尺度时序模块审计行为一致性，并通过带扰动的半监督 Mean-Teacher 学习。

Application-layer BSM evidence is exploited to associate fragmented pseudonyms through progressive behavioral consistency auditing. •Dynamic spatio-temporal GNN representation.We propose a more discriminative feature space and a collaborative framework comprising four specialized modules.

摘要称该方法在四种 Sybil 攻击场景、未标注比例 0.70–0.95 下优于对比方法，并在严重类别不平衡和超参数变化时保持稳定；全文提取到的实验依据目前只覆盖硬件配置，具体指标需补读结果表。

3) Experimental Details and Baselines:All experiments are conducted on an NVIDIA GeForce RTX 5090 GPU with 32 GB VRAM.