Amulet: a Python Library for Assessing Interactions Among ML Defenses and Risks
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915603653066752 |
|---|---|
| author | Waheed, Asim Duddu, Vasisht Zhang, Rui Szyller, Sebastian |
| author_facet | Waheed, Asim Duddu, Vasisht Zhang, Rui Szyller, Sebastian |
| contents | Machine learning (ML) models are susceptible to various risks to security, privacy, and fairness. Most defenses are designed to protect against each risk individually (intended interactions) but can inadvertently affect susceptibility to other unrelated risks (unintended interactions). We introduce Amulet, the first Python library for evaluating both intended and unintended interactions among ML defenses and risks. Amulet is comprehensive by including representative attacks, defenses, and metrics; extensible to new modules due to its modular design; consistent with a user-friendly API template for inputs and outputs; and applicable for evaluating novel interactions. By satisfying all four properties, Amulet offers a unified foundation for studying how defenses interact, enabling the first systematic evaluation of unintended interactions across multiple risks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_12386 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Amulet: a Python Library for Assessing Interactions Among ML Defenses and Risks Waheed, Asim Duddu, Vasisht Zhang, Rui Szyller, Sebastian Cryptography and Security Artificial Intelligence Machine learning (ML) models are susceptible to various risks to security, privacy, and fairness. Most defenses are designed to protect against each risk individually (intended interactions) but can inadvertently affect susceptibility to other unrelated risks (unintended interactions). We introduce Amulet, the first Python library for evaluating both intended and unintended interactions among ML defenses and risks. Amulet is comprehensive by including representative attacks, defenses, and metrics; extensible to new modules due to its modular design; consistent with a user-friendly API template for inputs and outputs; and applicable for evaluating novel interactions. By satisfying all four properties, Amulet offers a unified foundation for studying how defenses interact, enabling the first systematic evaluation of unintended interactions across multiple risks. |
| title | Amulet: a Python Library for Assessing Interactions Among ML Defenses and Risks |
| topic | Cryptography and Security Artificial Intelligence |
| url | https://arxiv.org/abs/2509.12386 |