Identifying Backdoored Graphs in Graph Neural Network Training: An Explanation-Based Approach with Novel Metrics
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866909030249660416 |
|---|---|
| author | Downer, Jane Wang, Ren Wang, Binghui |
| author_facet | Downer, Jane Wang, Ren Wang, Binghui |
| contents | Graph Neural Networks (GNNs) have gained popularity in numerous domains, yet they are vulnerable to backdoor attacks that can compromise their performance and ethical application. The detection of these attacks is crucial for maintaining the reliability and security of GNN classification tasks, but existing methods are often inflexible, relying on single metrics that fail to capture the full range of backdoor behaviors. Recognizing the challenge in detecting such intrusions, we devised a novel detection method that creatively leverages graph-level explanations. By extracting and transforming secondary outputs from GNN explanation mechanisms, we developed seven innovative metrics for effective detection of backdoor attacks on GNNs. Additionally, we develop an adaptive attack to rigorously evaluate our approach. We test our method on multiple benchmark datasets and examine its efficacy against various attack models. Our results show that our method can achieve high detection performance, marking a significant advancement in safeguarding GNNs against backdoor attacks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_18136 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Identifying Backdoored Graphs in Graph Neural Network Training: An Explanation-Based Approach with Novel Metrics Downer, Jane Wang, Ren Wang, Binghui Machine Learning Artificial Intelligence Graph Neural Networks (GNNs) have gained popularity in numerous domains, yet they are vulnerable to backdoor attacks that can compromise their performance and ethical application. The detection of these attacks is crucial for maintaining the reliability and security of GNN classification tasks, but existing methods are often inflexible, relying on single metrics that fail to capture the full range of backdoor behaviors. Recognizing the challenge in detecting such intrusions, we devised a novel detection method that creatively leverages graph-level explanations. By extracting and transforming secondary outputs from GNN explanation mechanisms, we developed seven innovative metrics for effective detection of backdoor attacks on GNNs. Additionally, we develop an adaptive attack to rigorously evaluate our approach. We test our method on multiple benchmark datasets and examine its efficacy against various attack models. Our results show that our method can achieve high detection performance, marking a significant advancement in safeguarding GNNs against backdoor attacks. |
| title | Identifying Backdoored Graphs in Graph Neural Network Training: An Explanation-Based Approach with Novel Metrics |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2403.18136 |