Attesting Distributional Properties of Training Data for Machine Learning
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_ | 1866911831747985408 |
|---|---|
| author | Duddu, Vasisht Das, Anudeep Khayata, Nora Yalame, Hossein Schneider, Thomas Asokan, N. |
| author_facet | Duddu, Vasisht Das, Anudeep Khayata, Nora Yalame, Hossein Schneider, Thomas Asokan, N. |
| contents | The success of machine learning (ML) has been accompanied by increased concerns about its trustworthiness. Several jurisdictions are preparing ML regulatory frameworks. One such concern is ensuring that model training data has desirable distributional properties for certain sensitive attributes. For example, draft regulations indicate that model trainers are required to show that training datasets have specific distributional properties, such as reflecting diversity of the population. We propose the notion of property attestation allowing a prover (e.g., model trainer) to demonstrate relevant distributional properties of training data to a verifier (e.g., a customer) without revealing the data. We present an effective hybrid property attestation combining property inference with cryptographic mechanisms. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2308_09552 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Attesting Distributional Properties of Training Data for Machine Learning Duddu, Vasisht Das, Anudeep Khayata, Nora Yalame, Hossein Schneider, Thomas Asokan, N. Cryptography and Security Machine Learning The success of machine learning (ML) has been accompanied by increased concerns about its trustworthiness. Several jurisdictions are preparing ML regulatory frameworks. One such concern is ensuring that model training data has desirable distributional properties for certain sensitive attributes. For example, draft regulations indicate that model trainers are required to show that training datasets have specific distributional properties, such as reflecting diversity of the population. We propose the notion of property attestation allowing a prover (e.g., model trainer) to demonstrate relevant distributional properties of training data to a verifier (e.g., a customer) without revealing the data. We present an effective hybrid property attestation combining property inference with cryptographic mechanisms. |
| title | Attesting Distributional Properties of Training Data for Machine Learning |
| topic | Cryptography and Security Machine Learning |
| url | https://arxiv.org/abs/2308.09552 |