arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2108.08421cs.CVcs.LG
收藏

利用多目标关系检测复杂场景中的对抗攻击

Exploiting Multi-Object Relationships for Detecting Adversarial Attacks in Complex Scenes

University of California, Riverside(加州大学河滨分校)

Mingjun Yin, Shasha Li, Zikui Cai, Chengyu Song, M. Salman Asif, Amit K. Roy-Chowdhury, Srikanth V. Krishnamurthy

摘要:

众所周知,部署深度神经网络(DNN)的视觉系统容易受到对抗性示例的攻击。最近的研究已经表明,检查输入数据中的固有错误是检测对抗攻击(例如,通过检查复杂场景中的对象共现关系)。然而,现有的方法都与特定的模型相联系,不具有普遍性。出于观察自然场景图像的语言描述已经捕获的对象共现关系,可以通过语言模型学习,我们开发了一种新的方法来执行上下文一致性检查使用这样的语言模型。我们的方法的区别在于,它独立于部署的对象检测器,但在检测具有多个对象的实际场景中的对抗性示例方面提供了非常高的准确性。

英文摘要:

Vision systems that deploy Deep Neural Networks (DNNs) are known to be vulnerable to adversarial examples. Recent research has shown that checking the intrinsic consistencies in the input data is a promising way to detect adversarial attacks (e.g., by checking the object co-occurrence relationships in complex scenes). However, existing approaches are tied to specific models and do not offer generalizability. Motivated by the observation that language descriptions of natural scene images have already captured the object co-occurrence relationships that can be learned by a language model, we develop a novel approach to perform context consistency checks using such language models. The distinguishing aspect of our approach is that it is independent of the deployed object detector and yet offers very high accuracy in terms of detecting adversarial examples in practical scenes with multiple objects.

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。

↑