arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2202.11287cs.CVcs.CRcs.LG
收藏

LPF-Defense:基于频率分析的3D对抗防御

LPF-Defense: 3D Adversarial Defense based on Frequency Analysis

Sharif University of Technology(谢里夫理工大学)

Hanieh Naderi, Kimia Noorbakhsh, Arian Etemadi, Shohreh Kasaei

摘要:

虽然三维点云分类最近已被广泛部署在不同的应用场景中,但它仍然非常容易受到对抗攻击。这增加了3D模型在面对对抗攻击时的鲁棒训练的重要性。基于我们对现有对抗攻击性能的分析,发现更多的对抗扰动出现在输入数据的中高频分量。因此,通过在训练阶段抑制高频内容,提高了模型对对抗性示例的鲁棒性。实验结果表明,该防御方法降低了PointNet、PointNet++、、和DGCNN模型上六种攻击的成功率。特别是,与最先进的方法相比,在drop 100攻击下分类准确率平均提高了3.8%,在drop 200攻击下提高了4.26%。与其他可用的方法相比,该方法还提高了原始数据集上的模型精度。

英文摘要:

Although 3D point cloud classification has recently been widely deployed in different application scenarios, it is still very vulnerable to adversarial attacks. This increases the importance of robust training of 3D models in the face of adversarial attacks. Based on our analysis on the performance of existing adversarial attacks, more adversarial perturbations are found in the mid and high-frequency components of input data. Therefore, by suppressing the high-frequency content in the training phase, the models robustness against adversarial examples is improved. Experiments showed that the proposed defense method decreases the success rate of six attacks on PointNet, PointNet++ ,, and DGCNN models. In particular, improvements are achieved with an average increase of classification accuracy by 3.8 % on drop100 attack and 4.26 % on drop200 attack compared to the state-of-the-art methods. The method also improves models accuracy on the original dataset compared to other available 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。

↑