Vom 20.12.2025 bis 11.01.2026 ist die Universitätsbibliothek geschlossen. Ab dem 12.01.2026 gelten wieder die regulären Öffnungszeiten. Ausnahme: Medizinische Hauptbibliothek und Zentralbibliothek sind bereits ab 05.01.2026 wieder geöffnet. Weitere Informationen

Treffer: Amulet: a Python Library for Assessing Interactions Among ML Defenses and Risks

Title:
Amulet: a Python Library for Assessing Interactions Among ML Defenses and Risks
Authors:
Waheed, Asim, Duddu, Vasisht, Zhang, Rui, Szyller, Sebastian
Publication Year:
2025
Subject Terms:
Cryptography and Security, Artificial Intelligence
Document Type:
Report Working Paper
Access URL:
http://arxiv.org/abs/2509.12386
Accession Number:
edsarx.2509.12386
Database:
arXiv

Weitere Informationen

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.
10 pages, 4 figures