Amulet: a Python Library for Assessing Interactions Among ML Defenses and Risks
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 45 of its 66 references that are in the map. First posted on arXiv 15 Sep 2025.
Builds on
45 of 66 references.
References · 45
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2024The Llama 3 Herd of Modelscited by 14,715
- 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
- 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
- 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,349
- 2014Deep Learning Face Attributes in the Wildcited by 3,693
- 2016Deep Learning with Differential Privacycited by 2,728
- 2020Extracting Training Data from Large Language Modelscited by 2,189
- 2021Membership Inference Attacks From First Principlescited by 878
- 2018Mitigating Unwanted Biases with Adversarial Learningcited by 663
- 2016Stealing Machine Learning Models via Prediction APIscited by 619
- 2020Captum: A unified and generic model interpretability library for PyTorchcited by 547
33 more
- 2018Exploiting Unintended Feature Leakage in Collaborative Learningcited by 520
- 2018Spectral Signatures in Backdoor Attackscited by 484
- 2021Opacus: User-Friendly Differential Privacy Library in PyTorchcited by 383
- 2018Turning Your Weakness Into a Strength: Watermarking Deep Neural Networks by Backdooringcited by 357
- 2018AI Fairness 360: An Extensible Toolkit for Detecting, Understanding, and Mitigating Unwanted Algorithmic Biascited by 319
- 2018Adversarially Robust Generalization Requires More Datacited by 318
- 2018Knockoff Nets: Stealing Functionality of Black-Box Modelscited by 292
- 2020ONION: A Simple and Effective Defense Against Textual Backdoor Attackscited by 263
- 2021Anti-Backdoor Learning: Training Clean Models on Poisoned Datacited by 263
- 2021Adversarial Neuron Pruning Purifies Backdoored Deep Modelscited by 235
- 2018Adversarial Robustness Toolbox v1.0.0cited by 215
- 2019Efficient Task-Specific Data Valuation for Nearest Neighbor Algorithmscited by 148
- 2019Privacy Risks of Securing Machine Learning Models against Adversarial Examplescited by 141
- 2016Technical Report on the CleverHans v2.1.0 Adversarial Examples Librarycited by 124
- 2021Dataset Inference: Ownership Resolution in Machine Learningcited by 116
- 2019Deep Neural Network Fingerprinting by Conferrable Adversarial Examplescited by 93
- 2020On the Effectiveness of Mitigating Data Poisoning Attacks with Gradient Shapingcited by 83
- 2019Data Poisoning against Differentially-Private Learners: Attacks and Defensescited by 78
- 2022A Unified Evaluation of Textual Backdoor Learning: Frameworks and Benchmarkscited by 74
- 2023Fairlearn: Assessing and Improving Fairness of AI Systemscited by 74
- 2020ML Privacy Meter: Aiding Regulatory Compliance by Quantifying the Privacy Risks of Machine Learningcited by 70
- 2019advertorch v0.1: An Adversarial Robustness Toolbox based on PyTorchcited by 69
- 2016Learning to Pivot with Adversarial Networkscited by 55
- 2020Robustness May Be at Odds with Fairness: An Empirical Study on Class-wise Accuracycited by 45
- 2020TrojanZoo: Towards Unified, Holistic, and Practical Evaluation of Neural Backdoorscited by 30
- 2023Privacy and Fairness in Federated Learning: on the Perspective of Trade-offcited by 26
- 2022Dissecting Distribution Inferencecited by 15
- 2023DPMLBench: Holistic Evaluation of Differentially Private Machine Learningcited by 13
- 2022Conflicting Interactions Among Protection Mechanisms for Machine Learning Modelscited by 12
- 2022On the Alignment of Group Fairness with Attribute Privacycited by 9
- 2022On the Robustness of Dataset Inferencecited by 8
- 2023SoK: Unintended Interactions among Machine Learning Defenses and Riskscited by 6
- 2024Combining Machine Learning Defenses without Conflictscited by 2
Built on by
Citing papers per year: 2025: 1.
1 paper.