Bayes-Nash Generative Privacy Against Membership Inference Attacks
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_ | 1866908443672051712 |
|---|---|
| author | Zhang, Tao Venkatesaramani, Rajagopal De, Rajat K. Malin, Bradley A. Vorobeychik, Yevgeniy |
| author_facet | Zhang, Tao Venkatesaramani, Rajagopal De, Rajat K. Malin, Bradley A. Vorobeychik, Yevgeniy |
| contents | Membership inference attacks (MIAs) pose significant privacy risks by determining whether individual data is in a dataset. While differential privacy (DP) mitigates these risks, it has limitations including limited resolution in expressing privacy-utility tradeoffs and intractable sensitivity calculations for tight guarantees. We propose a game-theoretic framework modeling privacy protection as a Bayesian game between defender and attacker, where privacy loss corresponds to the attacker's membership inference ability. To address strategic complexity, we represent the defender's mixed strategy as a neural network generator mapping private datasets to public representations (e.g., noisy statistics) and the attacker's strategy as a discriminator making membership claims. This \textit{general-sum Generative Adversarial Network} trains iteratively through alternating updates, yielding \textit{Bayes-Nash Generative Privacy (BNGP)} strategies. BNGP avoids worst-case privacy proofs such as sensitivity calculations, supports correlated mechanism compositions, handles heterogeneous attacker preferences. Empirical studies on sensitive dataset summary statistics show our approach significantly outperforms state-of-the-art methods by generating stronger attacks and achieving better privacy-utility tradeoffs. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_07414 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Bayes-Nash Generative Privacy Against Membership Inference Attacks Zhang, Tao Venkatesaramani, Rajagopal De, Rajat K. Malin, Bradley A. Vorobeychik, Yevgeniy Cryptography and Security Membership inference attacks (MIAs) pose significant privacy risks by determining whether individual data is in a dataset. While differential privacy (DP) mitigates these risks, it has limitations including limited resolution in expressing privacy-utility tradeoffs and intractable sensitivity calculations for tight guarantees. We propose a game-theoretic framework modeling privacy protection as a Bayesian game between defender and attacker, where privacy loss corresponds to the attacker's membership inference ability. To address strategic complexity, we represent the defender's mixed strategy as a neural network generator mapping private datasets to public representations (e.g., noisy statistics) and the attacker's strategy as a discriminator making membership claims. This \textit{general-sum Generative Adversarial Network} trains iteratively through alternating updates, yielding \textit{Bayes-Nash Generative Privacy (BNGP)} strategies. BNGP avoids worst-case privacy proofs such as sensitivity calculations, supports correlated mechanism compositions, handles heterogeneous attacker preferences. Empirical studies on sensitive dataset summary statistics show our approach significantly outperforms state-of-the-art methods by generating stronger attacks and achieving better privacy-utility tradeoffs. |
| title | Bayes-Nash Generative Privacy Against Membership Inference Attacks |
| topic | Cryptography and Security |
| url | https://arxiv.org/abs/2410.07414 |