arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2004.12519cs.LGstat.ML
收藏

深特征分布的可转移扰动

Transferable Perturbations of Deep Feature Distributions

Duke University(杜克大学)

Nathan Inkawhich, Kevin J Liang, Lawrence Carin, Yiran Chen

摘要:

目前几乎所有对CNN分类器的对抗攻击都依赖于从网络输出层获得的信息。这项工作提出了一种新的对抗攻击的基础上建模和开发类和层的深度特征分布。我们为不设防的ImageNet模型实现了最先进的基于黑盒传输的攻击结果。此外,我们优先考虑攻击过程的可解释性和可解释性。我们的方法提供了一个分析对抗攻击如何改变CNN的中间特征分布,以及逐层和逐类特征分布分离性/纠缠的措施。我们还在CNN架构中概念化了从任务/数据特定到模型特定特征的过渡,这直接影响了对抗性示例的可转移性。

英文摘要:

Almost all current adversarial attacks of CNN classifiers rely on information derived from the output layer of the network. This work presents a new adversarial attack based on the modeling and exploitation of class-wise and layer-wise deep feature distributions. We achieve state-of-the-art targeted blackbox transfer-based attack results for undefended ImageNet models. Further, we place a priority on explainability and interpretability of the attacking process. Our methodology affords an analysis of how adversarial attacks change the intermediate feature distributions of CNNs, as well as a measure of layer-wise and class-wise feature distributional separability/entanglement. We also conceptualize a transition from task/data-specific to model-specific features within a CNN architecture that directly impacts the transferability of adversarial examples.

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。

↑