LPF-Defense: 3D Adversarial Defense based on Frequency Analysis
This addresses the problem of adversarial robustness for 3D point cloud models, which is incremental as it builds on frequency analysis to enhance existing defenses.
The paper tackles the vulnerability of 3D point cloud classification models to adversarial attacks by proposing a defense method that suppresses high-frequency content during training, which improves robustness and increases classification accuracy by an average of 3.8% on drop100 and 4.26% on drop200 attacks compared to state-of-the-art methods.
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.