Visual Privacy Auditing with Diffusion Models
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866909530630127616 |
|---|---|
| author | Schwethelm, Kristian Kaiser, Johannes Knolle, Moritz Lockfisch, Sarah Rueckert, Daniel Ziller, Alexander |
| author_facet | Schwethelm, Kristian Kaiser, Johannes Knolle, Moritz Lockfisch, Sarah Rueckert, Daniel Ziller, Alexander |
| contents | Data reconstruction attacks on machine learning models pose a substantial threat to privacy, potentially leaking sensitive information. Although defending against such attacks using differential privacy (DP) provides theoretical guarantees, determining appropriate DP parameters remains challenging. Current formal guarantees on the success of data reconstruction suffer from overly stringent assumptions regarding adversary knowledge about the target data, particularly in the image domain, raising questions about their real-world applicability. In this work, we empirically investigate this discrepancy by introducing a reconstruction attack based on diffusion models (DMs) that only assumes adversary access to real-world image priors and specifically targets the DP defense. We find that (1) real-world data priors significantly influence reconstruction success, (2) current reconstruction bounds do not model the risk posed by data priors well, and (3) DMs can serve as heuristic auditing tools for visualizing privacy leakage. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_07588 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Visual Privacy Auditing with Diffusion Models Schwethelm, Kristian Kaiser, Johannes Knolle, Moritz Lockfisch, Sarah Rueckert, Daniel Ziller, Alexander Machine Learning Cryptography and Security Data reconstruction attacks on machine learning models pose a substantial threat to privacy, potentially leaking sensitive information. Although defending against such attacks using differential privacy (DP) provides theoretical guarantees, determining appropriate DP parameters remains challenging. Current formal guarantees on the success of data reconstruction suffer from overly stringent assumptions regarding adversary knowledge about the target data, particularly in the image domain, raising questions about their real-world applicability. In this work, we empirically investigate this discrepancy by introducing a reconstruction attack based on diffusion models (DMs) that only assumes adversary access to real-world image priors and specifically targets the DP defense. We find that (1) real-world data priors significantly influence reconstruction success, (2) current reconstruction bounds do not model the risk posed by data priors well, and (3) DMs can serve as heuristic auditing tools for visualizing privacy leakage. |
| title | Visual Privacy Auditing with Diffusion Models |
| topic | Machine Learning Cryptography and Security |
| url | https://arxiv.org/abs/2403.07588 |