arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2104.09369cs.LGcs.AI
收藏

基于图的流量预测模型的对抗性扩散攻击

Adversarial Diffusion Attacks on Graph-based Traffic Prediction Models

College of Civil Engineering and Architecture, Zhejiang University(浙江大学建筑工程学院);Department of Civil and Environmental Engineering, Princeton University(普林斯顿大学土木与环境工程系);School of Engineering, Monash University(莫纳什大学工程学院);Department of Civil and Environmental Engineering, The Hong Kong Polytechnic University(香港理工大学土木与环境工程系)

Lyuyi Zhu, Kairui Feng, Ziyuan Pu, Wei Ma

摘要:

实时交通预测模型在智能移动系统中发挥着关键作用,并已广泛应用于路径引导、新兴移动服务和先进的交通管理系统。随着海量交通数据的可用性,基于神经网络的深度学习方法,特别是图卷积网络(GCN),在挖掘时空信息、实现高预测精度方面表现出了突出的性能。最近的研究揭示了GCN在对抗攻击下的脆弱性,而缺乏研究来了解基于GCN的流量预测模型的脆弱性问题。鉴于此,本文提出了一个新的任务--扩散攻击,研究基于GCN的流量预测模型的鲁棒性。扩散攻击的目的是选择和攻击一小部分节点,以降低整个预测模型的性能。为了进行扩散攻击,提出了一种新的攻击算法,该算法包括两个主要部分:1)用同时扰动随机近似(SPSA)逼近黑箱预测模型的梯度; 2)采用背包贪心算法选择攻击节点。在两个城市使用三种基于GCN的交通预测模型:St-Gcn、T-Gcn和A3 t-Gcn来检验所提出的算法。该算法在各种场景下的对抗攻击任务中表现出较高的效率,并且在DropOut、DropNode和DropEdge等丢弃正则化下仍能生成对抗样本。研究结果有助于提高基于GCN的交通预测模型的鲁棒性,更好地保护智能移动系统。我们的代码可在www.example.com上获得

英文摘要:

Real-time traffic prediction models play a pivotal role in smart mobility systems and have been widely used in route guidance, emerging mobility services, and advanced traffic management systems. With the availability of massive traffic data, neural network-based deep learning methods, especially the graph convolutional networks (GCN) have demonstrated outstanding performance in mining spatio-temporal information and achieving high prediction accuracy. Recent studies reveal the vulnerability of GCN under adversarial attacks, while there is a lack of studies to understand the vulnerability issues of the GCN-based traffic prediction models. Given this, this paper proposes a new task -- diffusion attack, to study the robustness of GCN-based traffic prediction models. The diffusion attack aims to select and attack a small set of nodes to degrade the performance of the entire prediction model. To conduct the diffusion attack, we propose a novel attack algorithm, which consists of two major components: 1) approximating the gradient of the black-box prediction model with Simultaneous Perturbation Stochastic Approximation (SPSA); 2) adapting the knapsack greedy algorithm to select the attack nodes. The proposed algorithm is examined with three GCN-based traffic prediction models: St-Gcn, T-Gcn, and A3t-Gcn on two cities. The proposed algorithm demonstrates high efficiency in the adversarial attack tasks under various scenarios, and it can still generate adversarial samples under the drop regularization such as DropOut, DropNode, and DropEdge. The research outcomes could help to improve the robustness of the GCN-based traffic prediction models and better protect the smart mobility systems. Our code is available at https://github.com/LYZ98/Adversarial-Diffusion-Attacks-on-Graph-based-Traffic-Prediction-Models

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。

↑