Adversarial Robustness of VAEs across Intersectional Subgroups
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916481274478592 |
|---|---|
| author | Ramanaik, Chethan Krishnamurthy Roy, Arjun Ntoutsi, Eirini |
| author_facet | Ramanaik, Chethan Krishnamurthy Roy, Arjun Ntoutsi, Eirini |
| contents | Despite advancements in Autoencoders (AEs) for tasks like dimensionality reduction, representation learning and data generation, they remain vulnerable to adversarial attacks. Variational Autoencoders (VAEs), with their probabilistic approach to disentangling latent spaces, show stronger resistance to such perturbations compared to deterministic AEs; however, their resilience against adversarial inputs is still a concern. This study evaluates the robustness of VAEs against non-targeted adversarial attacks by optimizing minimal sample-specific perturbations to cause maximal damage across diverse demographic subgroups (combinations of age and gender). We investigate two questions: whether there are robustness disparities among subgroups, and what factors contribute to these disparities, such as data scarcity and representation entanglement. Our findings reveal that robustness disparities exist but are not always correlated with the size of the subgroup. By using downstream gender and age classifiers and examining latent embeddings, we highlight the vulnerability of subgroups like older women, who are prone to misclassification due to adversarial perturbations pushing their representations toward those of other subgroups. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_03864 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Adversarial Robustness of VAEs across Intersectional Subgroups Ramanaik, Chethan Krishnamurthy Roy, Arjun Ntoutsi, Eirini Machine Learning Artificial Intelligence Despite advancements in Autoencoders (AEs) for tasks like dimensionality reduction, representation learning and data generation, they remain vulnerable to adversarial attacks. Variational Autoencoders (VAEs), with their probabilistic approach to disentangling latent spaces, show stronger resistance to such perturbations compared to deterministic AEs; however, their resilience against adversarial inputs is still a concern. This study evaluates the robustness of VAEs against non-targeted adversarial attacks by optimizing minimal sample-specific perturbations to cause maximal damage across diverse demographic subgroups (combinations of age and gender). We investigate two questions: whether there are robustness disparities among subgroups, and what factors contribute to these disparities, such as data scarcity and representation entanglement. Our findings reveal that robustness disparities exist but are not always correlated with the size of the subgroup. By using downstream gender and age classifiers and examining latent embeddings, we highlight the vulnerability of subgroups like older women, who are prone to misclassification due to adversarial perturbations pushing their representations toward those of other subgroups. |
| title | Adversarial Robustness of VAEs across Intersectional Subgroups |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2407.03864 |