低资源攻击框架可让动态图神经网络性能下降超42%
LoReTTA: A Low Resource Framework To Poison Continuous Time Dynamic Graphs
- 分两阶段攻击：先删关键边，再用保度负采样替换
- 平均降效29.47%，最高降幅达42.0%（MOOC数据集）
- 无需替代模型，隐蔽性强，可绕过主流防御
时间图神经网络（TGNNs）在金融预测、推荐系统和欺诈检测等高风险领域应用日益广泛，但其易受中毒攻击的特性带来严重安全威胁。我们提出LoReTTA（低资源两阶段时序攻击），一种针对连续时间动态图的新颖对抗攻击框架，在4个基准数据集和4种先进模型上平均使TGNN性能下降29.47%。该方法分两步：（1）使用16种时间重要性度量中的任意一种，移除高影响边以稀疏图结构；（2）通过我们提出的保度负采样算法，战略性地用对抗性负边替换被移除的边。其即插即用设计无需昂贵的替代模型，并满足现实中的不可察觉约束。实验显示，对MOOC、Wikipedia、UCI、Enron数据集的性能下降分别高达42.0%、31.5%、28.8%和15.6%。LoReTTA优于11种攻击基线，可逃逸4种主流异常检测系统，且对4种SotA对抗防御训练方法具有鲁棒性，验证了其有效性、隐蔽性和抗防御能力。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。