鲁棒多元时间序列预测：对抗攻击与防御机制
Robust Multivariate Time-Series Forecasting: Adversarial Attacks and Defense Mechanisms
AI总结：
本文研究多元时间序列预测中的对抗攻击与防御，提出稀疏对抗攻击模式，并通过随机平滑扩展和对抗训练算法提升模型鲁棒性，实验验证其攻击有效且防御优于基线。
摘要：
本工作研究针对多元概率预测模型的对抗攻击威胁以及可行的防御机制。我们的研究发现了一种新的攻击模式，该模式通过对少量其他时间序列的历史观测进行战略性、稀疏（不可察觉）的修改，从而对目标时间序列的预测产生负面影响。为了减轻此类攻击的影响，我们开发了两种防御策略。首先，我们将先前在分类任务中提出的随机平滑技术扩展到多元预测场景。其次，我们开发了一种对抗训练算法，该算法学习生成对抗样本，同时优化预测模型，以提高其对这种对抗模拟的鲁棒性。在真实世界数据集上的大量实验证实，我们的攻击方案具有强大威力，并且与基线防御机制相比，我们的防御算法更为有效。
英文摘要：
This work studies the threats of adversarial attack on multivariate probabilistic forecasting models and viable defense mechanisms. Our studies discover a new attack pattern that negatively impact the forecasting of a target time series via making strategic, sparse (imperceptible) modifications to the past observations of a small number of other time series. To mitigate the impact of such attack, we have developed two defense strategies. First, we extend a previously developed randomized smoothing technique in classification to multivariate forecasting scenarios. Second, we develop an adversarial training algorithm that learns to create adversarial examples and at the same time optimizes the forecasting model to improve its robustness against such adversarial simulation. Extensive experiments on real-world datasets confirm that our attack schemes are powerful and our defense algorithms are more effective compared with baseline defense mechanisms.
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。
