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

Asim Waheed, Vasisht Duddu, Rui Zhang, Sebastian Szyller
9/15/2025
cs.CRcs.AI

No confident code implementation found for this paper.

Abstract

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.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Threats and Defenses in Federated Learning Life Cycle: A Comprehensive Survey and Challenges

83% match2024

A Survey of Safety on Large Vision-Language Models: Attacks, Defenses and Evaluations

83% match1 repo2012025

On the Security and Privacy of Federated Learning: A Survey with Attacks, Defenses, Frameworks, Applications, and Future Directions

83% match2025

Deep Learning Under Siege: Identifying Security Vulnerabilities and Risk Mitigation Strategies

83% match2024

Adversarial Machine Learning: Attacks, Defenses, and Open Challenges

83% match2025

How Real Is Real? A Human Evaluation Framework for Unrestricted Adversarial Examples

82% match2024

Cite this paper

@article{waheed2025amulet,
  title  = {Amulet: a Python Library for Assessing Interactions Among ML Defenses and Risks},
  author = {Asim Waheed and Vasisht Duddu and Rui Zhang and Sebastian Szyller},
  year   = {2025},
  eprint = {2509.12386},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2509.12386v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2509.12386.svg)](https://codeofpaper.com/paper/2509.12386)

Discussion