GENADA：高效生成式时间序列对抗攻击框架
GENADA: efficient generative time series adversarial attack framework
- Moscow Independent Research Institute of Artificial Intelligence（莫斯科独立人工智能研究院）
- HSE University（高等经济大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
该研究针对时间序列分析深度学习模型的对抗攻击问题，提出GENADA框架，通过生成模型单次前向传播生成扰动，在保持攻击质量的同时缩短推理耗时，提升了攻击效率。
AI中文摘要：
深度学习模型被广泛应用于医疗、金融、能源系统及环境监测等领域的时间序列分析，但这些模型仍易受对抗攻击影响，微小的输入扰动会导致预测性能严重下降。常用的基于梯度的攻击（如迭代一阶方法）计算成本高，因为它们需要在多次迭代优化步骤中反复通过受害模型反向传播以计算输入梯度。本文提出了一种生成式对抗攻击框架GENADA，该框架学习生成模型以在单次前向传播中直接生成欺骗性扰动，并给出了其训练流程，变体包括单步和迭代生成式攻击方案。验证环节针对时间序列领域的多个神经模型和数据集，在受控的低维设置下开展，实验表明GENADA在达到与强基线相当的攻击质量的同时，推理阶段生成扰动所需时间更少。
英文摘要：
Deep learning models are widely used for time series analysis in domains such as healthcare, finance, energy systems, and environmental monitoring. However, these models remain vulnerable to adversarial attacks, where small input perturbations cause severe degradation in predictive performance. Commonly used gradient-based attacks, iterative first-order methods, are computationally burdensome, as they repeatedly backpropagate through the victim model to compute input gradients during a number of iterative refinement steps. We propose a GENerative ADversarial Attack (GENADA) that learns a generative model to produce deceptive perturbations directly in a single forward pass and a procedure to train it. Variants include single-step and iterative generative attack schemes. The validation considers attacks on several neural models and datasets in the time-series domain, a controlled, low-dimensional setting. Empirically, GENADA achieves comparable attack quality to strong baselines while requiring less time to generate perturbations during inference.
