Unveiling the Unseen: Exploring Whitebox Membership Inference through the Lens of Explainability
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_ | 1866909236347273216 |
|---|---|
| author | Li, Chenxi Kumar, Abhinav Guo, Zhen Hou, Jie Tourani, Reza |
| author_facet | Li, Chenxi Kumar, Abhinav Guo, Zhen Hou, Jie Tourani, Reza |
| contents | The increasing prominence of deep learning applications and reliance on personalized data underscore the urgent need to address privacy vulnerabilities, particularly Membership Inference Attacks (MIAs). Despite numerous MIA studies, significant knowledge gaps persist, particularly regarding the impact of hidden features (in isolation) on attack efficacy and insufficient justification for the root causes of attacks based on raw data features. In this paper, we aim to address these knowledge gaps by first exploring statistical approaches to identify the most informative neurons and quantifying the significance of the hidden activations from the selected neurons on attack accuracy, in isolation and combination. Additionally, we propose an attack-driven explainable framework by integrating the target and attack models to identify the most influential features of raw data that lead to successful membership inference attacks. Our proposed MIA shows an improvement of up to 26% on state-of-the-art MIA. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_01306 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Unveiling the Unseen: Exploring Whitebox Membership Inference through the Lens of Explainability Li, Chenxi Kumar, Abhinav Guo, Zhen Hou, Jie Tourani, Reza Machine Learning Cryptography and Security The increasing prominence of deep learning applications and reliance on personalized data underscore the urgent need to address privacy vulnerabilities, particularly Membership Inference Attacks (MIAs). Despite numerous MIA studies, significant knowledge gaps persist, particularly regarding the impact of hidden features (in isolation) on attack efficacy and insufficient justification for the root causes of attacks based on raw data features. In this paper, we aim to address these knowledge gaps by first exploring statistical approaches to identify the most informative neurons and quantifying the significance of the hidden activations from the selected neurons on attack accuracy, in isolation and combination. Additionally, we propose an attack-driven explainable framework by integrating the target and attack models to identify the most influential features of raw data that lead to successful membership inference attacks. Our proposed MIA shows an improvement of up to 26% on state-of-the-art MIA. |
| title | Unveiling the Unseen: Exploring Whitebox Membership Inference through the Lens of Explainability |
| topic | Machine Learning Cryptography and Security |
| url | https://arxiv.org/abs/2407.01306 |