arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2004.06383cs.LGstat.ML
收藏

扩展对抗攻击以产生对抗类概率分布

Extending Adversarial Attacks to Produce Adversarial Class Probability Distributions

University of the Basque Country UPV/EHU(巴斯克大学(UPV/EHU));Basque Center for Applied Mathematics (BCAM)(巴斯克应用数学中心(BCAM))

Jon Vadillo, Roberto Santana, Jose A. Lozano

摘要:

尽管深度学习模型在广泛的人工智能任务中具有出色的性能和泛化水平,但已经证明,这些模型很容易被添加到自然输入中的不可感知但恶意的扰动所欺骗。这些改变的输入在文献中被称为对抗性示例。在本文中,我们提出了一种新的概率框架来推广和扩展对抗攻击,以便在将攻击方法应用于大量输入时为类产生所需的概率分布。这种新颖的攻击范例为对手提供了对目标模型的更大控制,从而在广泛的场景中暴露了传统范例无法进行的针对深度学习模型的威胁。我们介绍了四种不同的策略来有效地产生这样的攻击,并通过扩展多个对抗攻击算法来说明我们的方法。我们还通过实验验证了我们的方法的口述命令分类任务和推文情感分类任务,两个典型的机器学习问题,在音频和文本域,分别。我们的研究结果表明,我们可以接近任何概率分布的类,同时保持较高的欺骗率,甚至防止被检测到的标签移位检测方法的攻击。

英文摘要:

Despite the remarkable performance and generalization levels of deep learning models in a wide range of artificial intelligence tasks, it has been demonstrated that these models can be easily fooled by the addition of imperceptible yet malicious perturbations to natural inputs. These altered inputs are known in the literature as adversarial examples. In this paper, we propose a novel probabilistic framework to generalize and extend adversarial attacks in order to produce a desired probability distribution for the classes when we apply the attack method to a large number of inputs. This novel attack paradigm provides the adversary with greater control over the target model, thereby exposing, in a wide range of scenarios, threats against deep learning models that cannot be conducted by the conventional paradigms. We introduce four different strategies to efficiently generate such attacks, and illustrate our approach by extending multiple adversarial attack algorithms. We also experimentally validate our approach for the spoken command classification task and the Tweet emotion classification task, two exemplary machine learning problems in the audio and text domain, respectively. Our results demonstrate that we can closely approximate any probability distribution for the classes while maintaining a high fooling rate and even prevent the attacks from being detected by label-shift detection methods.

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。

↑