BACKTIME：针对多元时间序列预测的后门攻击
BACKTIME: Backdoor Attacks on Multivariate Time Series Forecasting
AI总结：
本文提出BackTime后门攻击方法，通过识别易受攻击时间戳并利用GNN触发器生成器自适应合成隐蔽触发器，实现对多元时间序列预测模型的恶意操控。
摘要：
多元时间序列（MTS）预测是一项基础任务，在交通、气候和流行病学等众多现实应用中具有广泛用途。尽管已经为这一任务开发了大量强大的深度学习模型，但很少有工作探索MTS预测模型对恶意攻击的鲁棒性，而这对于其在高风险场景中的可信部署至关重要。为弥补这一空白，我们深入研究针对MTS预测模型的后门攻击，并提出一种名为BackTime的有效攻击方法。通过向MTS数据中微妙地注入少量隐蔽触发器，BackTime能够根据攻击者的意图改变预测模型的输出。具体而言，BackTime首先识别数据中易受攻击的时间戳用于投毒，然后通过求解一个基于GNN触发器生成器的双层优化问题，自适应地合成隐蔽且有效的触发器。在多个数据集和最先进的MTS预测模型上的大量实验证明了BackTime攻击的有效性、通用性和隐蔽性。代码可在https://github.com/xiaolin-cs/BackTime获取。
英文摘要：
Multivariate Time Series (MTS) forecasting is a fundamental task with numerous real-world applications, such as transportation, climate, and epidemiology. While a myriad of powerful deep learning models have been developed for this task, few works have explored the robustness of MTS forecasting models to malicious attacks, which is crucial for their trustworthy employment in high-stake scenarios. To address this gap, we dive deep into the backdoor attacks on MTS forecasting models and propose an effective attack method named BackTime.By subtly injecting a few stealthy triggers into the MTS data, BackTime can alter the predictions of the forecasting model according to the attacker's intent. Specifically, BackTime first identifies vulnerable timestamps in the data for poisoning, and then adaptively synthesizes stealthy and effective triggers by solving a bi-level optimization problem with a GNN-based trigger generator. Extensive experiments across multiple datasets and state-of-the-art MTS forecasting models demonstrate the effectiveness, versatility, and stealthiness of \method{} attacks. The code is available at \url{https://github.com/xiaolin-cs/BackTime}.
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。
