SoK: Unintended Interactions among Machine Learning Defenses and Risks
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2023
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866909160651620352 |
|---|---|
| author | Duddu, Vasisht Szyller, Sebastian Asokan, N. |
| author_facet | Duddu, Vasisht Szyller, Sebastian Asokan, N. |
| contents | Machine learning (ML) models cannot neglect risks to security, privacy, and fairness. Several defenses have been proposed to mitigate such risks. When a defense is effective in mitigating one risk, it may correspond to increased or decreased susceptibility to other risks. Existing research lacks an effective framework to recognize and explain these unintended interactions. We present such a framework, based on the conjecture that overfitting and memorization underlie unintended interactions. We survey existing literature on unintended interactions, accommodating them within our framework. We use our framework to conjecture on two previously unexplored interactions, and empirically validate our conjectures. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2312_04542 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | SoK: Unintended Interactions among Machine Learning Defenses and Risks Duddu, Vasisht Szyller, Sebastian Asokan, N. Cryptography and Security Machine Learning Machine learning (ML) models cannot neglect risks to security, privacy, and fairness. Several defenses have been proposed to mitigate such risks. When a defense is effective in mitigating one risk, it may correspond to increased or decreased susceptibility to other risks. Existing research lacks an effective framework to recognize and explain these unintended interactions. We present such a framework, based on the conjecture that overfitting and memorization underlie unintended interactions. We survey existing literature on unintended interactions, accommodating them within our framework. We use our framework to conjecture on two previously unexplored interactions, and empirically validate our conjectures. |
| title | SoK: Unintended Interactions among Machine Learning Defenses and Risks |
| topic | Cryptography and Security Machine Learning |
| url | https://arxiv.org/abs/2312.04542 |