通过多任务输出不一致性检测对抗攻击，效率高且效果好。
Multi-Task Consistency-based Detection of Adversarial Attacks
- 利用多个视觉任务输出的不一致来识别对抗样本。
- 在BDD100k数据集上实现99.9%的检测ROC-AUC。
- 适合资源受限场景，如自动驾驶中的实时防御。
深度神经网络在众多视觉感知系统中已成功部署，但其对对抗攻击的脆弱性引发了对其实际应用的担忧，尤其是在自动驾驶领域。现有防御方法通常成本高昂，难以在资源受限的应用中部署。本文提出一种高效且有效的对抗攻击检测方案，利用复杂视觉系统中的多任务感知特性。通过分析多个视觉任务（如目标检测与实例分割）之间的推理输出不一致性来检测对抗扰动。为此，我们设计了一种一致性评分指标以量化任务间不一致程度，并提出一种方法选择最优模型对以提升检测效果。我们在BDD100k验证集上针对PGD攻击评估了该防御方案，实验结果表明，在所考虑的攻击者模型下，检测的ROC-AUC达到99.9%。
原文摘要 · Abstract (English)
Deep Neural Networks (DNNs) have found successful deployment in numerous vision perception systems. However, their susceptibility to adversarial attacks has prompted concerns regarding their practical applications, specifically in the context of autonomous driving. Existing defenses often suffer from cost inefficiency, rendering their deployment impractical for resource-constrained applications. In this work, we propose an efficient and effective adversarial attack detection scheme leveraging the multi-task perception within a complex vision system. Adversarial perturbations are detected by the inconsistencies between the inference outputs of multiple vision tasks, e.g., object detection and instance segmentation. To this end, we developed a consistency score metric to measure the inconsistency between vision tasks. Next, we designed an approach to select the best model pairs for detecting inconsistencies effectively. Finally, we evaluated our defense against PGD attacks across multiple vision models on the BDD100k validation dataset. The experimental results demonstrated that our defense achieved a ROC-AUC performance of 99.9% detection within the considered attacker model.
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。