Abstract
We present a generic Reinforcement Learning (RL) framework optimized for crafting adversarial attacks on different model types spanning from ECG signal analysis (1D), image classification (2D), and video classification (3D). The framework focuses on identifying sensitive regions and inducing misclassifications with minimal distortions and various distortion types. The novel RL method outperforms state-of-the-art methods for all three applications, proving its efficiency. Our RL approach produces superior localization masks, enhancing interpretability for image classification and ECG analysis models. For applications such as ECG analysis, our platform highlights critical ECG segments for clinicians while ensuring resilience against prevalent distortions. This comprehensive tool aims to bolster both resilience with adversarial training and transparency across varied applications and data types.
Abstract (translated)
我们提出了一个通用的强化学习(RL)框架,针对不同模型类型的攻击进行优化,包括心电图信号分析(1D)、图像分类(2D)和视频分类(3D)。该框架专注于识别敏感区域,通过最小程度的扭曲和各种扭曲类型来诱导误分类。与最先进的 methods 相比,新RL 方法在所有三个应用中都表现出色,证明了其效率。我们的RL方法产生了卓越的局部化掩码,增强了图像分类和心电图分析模型的可解释性。对于心电图分析等应用,我们的平台在确保对常见扭曲的 resilience 同时,使临床医生关注的ECG段具有更高的鲁棒性。这一全面的工具旨在通过对抗性训练增强韧性和跨应用和数据类型的透明度。
URL
https://arxiv.org/abs/2403.18985