arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2104.05808cs.CR
收藏

一种针对三维点云分类器的后门攻击

A Backdoor Attack against 3D Point Cloud Classifiers

Zhen Xiang, David J. Miller, Siheng Chen, Xi Li, George Kesidis

摘要:

由于3D传感器在安全关键应用中的普及,3D点云(PC)分类器的脆弱性已成为一个严重的问题。现有的针对3D PC分类器的对抗攻击都是测试时规避(TTE)攻击,其目的是利用分类器的知识诱导测试时错误分类。但是,由于受害者分类器通常无法被攻击者访问,因此在实践中威胁大大减少,因为PC TTE通常具有较差的可转移性。在这里,我们提出了第一个针对PC分类器的后门攻击(BA)。最初针对图像提出,BA毒害受害者分类器的训练集,使得每当攻击者的后门模式存在于给定的输入样本中时,分类器学习决定攻击者的目标类。值得注意的是,BA不需要受害者分类器的知识。与图像BA不同,我们建议将一组点插入PC中,作为为3D PC定制的强大后门模式。这样的集群也与物理攻击一致(即,与场景中的捕获对象)。我们使用一个独立训练的代理分类器优化集群的位置,并选择集群的局部几何形状,以避免可能的PC预处理和PC异常检测器(AD)。在实验中,我们的BA实现了一致的高成功率(> 87%),并显示出对最先进的PC AD的回避。

英文摘要:

Vulnerability of 3D point cloud (PC) classifiers has become a grave concern due to the popularity of 3D sensors in safety-critical applications. Existing adversarial attacks against 3D PC classifiers are all test-time evasion (TTE) attacks that aim to induce test-time misclassifications using knowledge of the classifier. But since the victim classifier is usually not accessible to the attacker, the threat is largely diminished in practice, as PC TTEs typically have poor transferability. Here, we propose the first backdoor attack (BA) against PC classifiers. Originally proposed for images, BAs poison the victim classifier's training set so that the classifier learns to decide to the attacker's target class whenever the attacker's backdoor pattern is present in a given input sample. Significantly, BAs do not require knowledge of the victim classifier. Different from image BAs, we propose to insert a cluster of points into a PC as a robust backdoor pattern customized for 3D PCs. Such clusters are also consistent with a physical attack (i.e., with a captured object in a scene). We optimize the cluster's location using an independently trained surrogate classifier and choose the cluster's local geometry to evade possible PC preprocessing and PC anomaly detectors (ADs). Experimentally, our BA achieves a uniformly high success rate (> 87%) and shows evasiveness against state-of-the-art PC ADs.

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。

↑