DeBUGCN -- Detecting Backdoors in CNNs Using Graph Convolutional Networks
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866912247258808320 |
|---|---|
| author | Vartak, Akash Hossain, Khondoker Murad Oates, Tim |
| author_facet | Vartak, Akash Hossain, Khondoker Murad Oates, Tim |
| contents | Deep neural networks (DNNs) are becoming commonplace in critical applications, making their susceptibility to backdoor (trojan) attacks a significant problem. In this paper, we introduce a novel backdoor attack detection pipeline, detecting attacked models using graph convolution networks (DeBUGCN). To the best of our knowledge, ours is the first use of GCNs for trojan detection. We use the static weights of a DNN to create a graph structure of its layers. A GCN is then used as a binary classifier on these graphs, yielding a trojan or clean determination for the DNN. To demonstrate the efficacy of our pipeline, we train hundreds of clean and trojaned CNN models on the MNIST handwritten digits and CIFAR-10 image datasets, and show the DNN classification results using DeBUGCN. For a true In-the-Wild use case, our pipeline is evaluated on the TrojAI dataset which consists of various CNN architectures, thus showing the robustness and model-agnostic behaviour of DeBUGCN. Furthermore, on comparing our results on several datasets with state-of-the-art trojan detection algorithms, DeBUGCN is faster and more accurate. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_18592 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | DeBUGCN -- Detecting Backdoors in CNNs Using Graph Convolutional Networks Vartak, Akash Hossain, Khondoker Murad Oates, Tim Computer Vision and Pattern Recognition Machine Learning Deep neural networks (DNNs) are becoming commonplace in critical applications, making their susceptibility to backdoor (trojan) attacks a significant problem. In this paper, we introduce a novel backdoor attack detection pipeline, detecting attacked models using graph convolution networks (DeBUGCN). To the best of our knowledge, ours is the first use of GCNs for trojan detection. We use the static weights of a DNN to create a graph structure of its layers. A GCN is then used as a binary classifier on these graphs, yielding a trojan or clean determination for the DNN. To demonstrate the efficacy of our pipeline, we train hundreds of clean and trojaned CNN models on the MNIST handwritten digits and CIFAR-10 image datasets, and show the DNN classification results using DeBUGCN. For a true In-the-Wild use case, our pipeline is evaluated on the TrojAI dataset which consists of various CNN architectures, thus showing the robustness and model-agnostic behaviour of DeBUGCN. Furthermore, on comparing our results on several datasets with state-of-the-art trojan detection algorithms, DeBUGCN is faster and more accurate. |
| title | DeBUGCN -- Detecting Backdoors in CNNs Using Graph Convolutional Networks |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2502.18592 |