CloudFort: Enhancing Robustness of 3D Point Cloud Classification Against Backdoor Attacks via Spatial Partitioning and Ensemble Prediction
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866911848510521344 |
|---|---|
| author | Lan, Wenhao Yang, Yijun Shen, Haihua Li, Shan |
| author_facet | Lan, Wenhao Yang, Yijun Shen, Haihua Li, Shan |
| contents | The increasing adoption of 3D point cloud data in various applications, such as autonomous vehicles, robotics, and virtual reality, has brought about significant advancements in object recognition and scene understanding. However, this progress is accompanied by new security challenges, particularly in the form of backdoor attacks. These attacks involve inserting malicious information into the training data of machine learning models, potentially compromising the model's behavior. In this paper, we propose CloudFort, a novel defense mechanism designed to enhance the robustness of 3D point cloud classifiers against backdoor attacks. CloudFort leverages spatial partitioning and ensemble prediction techniques to effectively mitigate the impact of backdoor triggers while preserving the model's performance on clean data. We evaluate the effectiveness of CloudFort through extensive experiments, demonstrating its strong resilience against the Point Cloud Backdoor Attack (PCBA). Our results show that CloudFort significantly enhances the security of 3D point cloud classification models without compromising their accuracy on benign samples. Furthermore, we explore the limitations of CloudFort and discuss potential avenues for future research in the field of 3D point cloud security. The proposed defense mechanism represents a significant step towards ensuring the trustworthiness and reliability of point-cloud-based systems in real-world applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_14042 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | CloudFort: Enhancing Robustness of 3D Point Cloud Classification Against Backdoor Attacks via Spatial Partitioning and Ensemble Prediction Lan, Wenhao Yang, Yijun Shen, Haihua Li, Shan Computer Vision and Pattern Recognition The increasing adoption of 3D point cloud data in various applications, such as autonomous vehicles, robotics, and virtual reality, has brought about significant advancements in object recognition and scene understanding. However, this progress is accompanied by new security challenges, particularly in the form of backdoor attacks. These attacks involve inserting malicious information into the training data of machine learning models, potentially compromising the model's behavior. In this paper, we propose CloudFort, a novel defense mechanism designed to enhance the robustness of 3D point cloud classifiers against backdoor attacks. CloudFort leverages spatial partitioning and ensemble prediction techniques to effectively mitigate the impact of backdoor triggers while preserving the model's performance on clean data. We evaluate the effectiveness of CloudFort through extensive experiments, demonstrating its strong resilience against the Point Cloud Backdoor Attack (PCBA). Our results show that CloudFort significantly enhances the security of 3D point cloud classification models without compromising their accuracy on benign samples. Furthermore, we explore the limitations of CloudFort and discuss potential avenues for future research in the field of 3D point cloud security. The proposed defense mechanism represents a significant step towards ensuring the trustworthiness and reliability of point-cloud-based systems in real-world applications. |
| title | CloudFort: Enhancing Robustness of 3D Point Cloud Classification Against Backdoor Attacks via Spatial Partitioning and Ensemble Prediction |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2404.14042 |