Temporal Graph Neural Networks (TGNNs) are increasingly used in high-stakes domains, such as financial forecasting, recommendation systems, and fraud detection. However, their susceptibility to poisoning attacks poses a critical security risk. We introduce LoReTTA (Low Resource Two-phase Temporal Attack), a novel adversarial framework on Continuous-Time Dynamic Graphs, which degrades TGNN performance by an average of 29.47% across 4 widely benchmark datasets and 4 State-of-the-Art (SotA) models. LoReTTA operates through a two-stage approach: (1) sparsify the graph by removing high-impact edges using any of the 16 tested temporal importance metrics, (2) strategically replace removed edges with adversarial negatives via LoReTTA's novel degree-preserving negative sampling algorithm. Our plug-and-play design eliminates the need for expensive surrogate models while adhering to realistic unnoticeability constraints. LoReTTA degrades performance by upto 42.0% on MOOC, 31.5% on Wikipedia, 28.8% on UCI, and 15.6% on Enron. LoReTTA outperforms 11 attack baselines, remains undetectable to 4 leading anomaly detection systems, and is robust to 4 SotA adversarial defense training methods, establishing its effectiveness, unnoticeability, and robustness.

翻译：时序图神经网络（TGNNs）在金融预测、推荐系统及欺诈检测等高风险领域中的应用日益广泛，但其对投毒攻击的脆弱性构成了严重的安全威胁。本文提出LoReTTA（低资源两阶段时序攻击），一种针对连续时间动态图的新型对抗性框架，该框架在4个广泛使用的基准数据集和4种最先进（SotA）模型上，平均将TGNN性能降低29.47%。LoReTTA通过两阶段方法实现攻击：（1）利用16种已测试的时序重要性指标中的任意一种，移除高影响力边以稀疏化图结构；（2）通过LoReTTA新颖的度保持负采样算法，策略性地用对抗性负边替换被移除的边。我们的即插即用设计无需昂贵的代理模型，同时遵循实际的无感知性约束。LoReTTA在MOOC数据集上性能降低高达42.0%，在Wikipedia上为31.5%，在UCI上为28.8%，在Enron上为15.6%。LoReTTA优于11种攻击基线方法，对4种主流异常检测系统保持不可检测性，并能抵御4种SotA对抗性防御训练方法，从而验证了其有效性、无感知性和鲁棒性。