用生成模型一次前向计算生成对抗扰动，提速同时保持攻击效果
GENADA: efficient generative time series adversarial attack framework
- 训练生成模型直接产生成熟扰动，单次前向传播完成攻击
- 在多个时序模型与数据集上，攻击成功率媲美强基线，推理时间更短
- 适合需要高效生成对抗样本的场景，如模型安全测试
深度学习模型广泛应用于医疗、金融、能源系统和环境监测等时序数据分析领域。然而，这些模型仍易受对抗攻击影响，微小输入扰动会导致预测性能严重下降。常见的基于梯度的攻击方法（如迭代一阶方法）计算开销大，需多次反向传播以计算输入梯度。本文提出一种生成式对抗攻击框架 GENADA，通过训练生成模型，在单次前向传播中直接生成具有欺骗性的扰动。该框架包含单步与迭代两种生成攻击变体。在多个时序神经网络与数据集上的验证表明，GENADA 在攻击质量上可媲美强基线，且推理阶段生成扰动所需时间显著更少。
原文摘要 · Abstract (English)
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.
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。