Representation Magnitude has a Liability to Privacy Vulnerability
Fuente:
arXiv
Salvato in:
| Autori principali: | , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910538929274880 |
|---|---|
| author | Fang, Xingli Kim, Jung-Eun |
| author_facet | Fang, Xingli Kim, Jung-Eun |
| contents | The privacy-preserving approaches to machine learning (ML) models have made substantial progress in recent years. However, it is still opaque in which circumstances and conditions the model becomes privacy-vulnerable, leading to a challenge for ML models to maintain both performance and privacy. In this paper, we first explore the disparity between member and non-member data in the representation of models under common training frameworks. We identify how the representation magnitude disparity correlates with privacy vulnerability and address how this correlation impacts privacy vulnerability. Based on the observations, we propose Saturn Ring Classifier Module (SRCM), a plug-in model-level solution to mitigate membership privacy leakage. Through a confined yet effective representation space, our approach ameliorates models' privacy vulnerability while maintaining generalizability. The code of this work can be found here: \url{https://github.com/JEKimLab/AIES2024_SRCM} |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_16164 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Representation Magnitude has a Liability to Privacy Vulnerability Fang, Xingli Kim, Jung-Eun Machine Learning Artificial Intelligence Cryptography and Security Computer Vision and Pattern Recognition The privacy-preserving approaches to machine learning (ML) models have made substantial progress in recent years. However, it is still opaque in which circumstances and conditions the model becomes privacy-vulnerable, leading to a challenge for ML models to maintain both performance and privacy. In this paper, we first explore the disparity between member and non-member data in the representation of models under common training frameworks. We identify how the representation magnitude disparity correlates with privacy vulnerability and address how this correlation impacts privacy vulnerability. Based on the observations, we propose Saturn Ring Classifier Module (SRCM), a plug-in model-level solution to mitigate membership privacy leakage. Through a confined yet effective representation space, our approach ameliorates models' privacy vulnerability while maintaining generalizability. The code of this work can be found here: \url{https://github.com/JEKimLab/AIES2024_SRCM} |
| title | Representation Magnitude has a Liability to Privacy Vulnerability |
| topic | Machine Learning Artificial Intelligence Cryptography and Security Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2407.16164 |