# CANIFE: Crafting Canaries for Empirical Privacy Measurement in Federated Learning

arXiv: https://arxiv.org/abs/2210.02912 · HTML: https://mlsanity.com/paper/2210.02912/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- Builds on 46 of its 62 references that are in the map.
- First posted on arXiv 6 Oct 2022.

## Builds on (most cited first, 30 of 46)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [Advances and Open Problems in Federated Learning](https://mlsanity.com/paper/1912.04977/) (2019)
- [Categorical Reparameterization with Gumbel-Softmax](https://mlsanity.com/paper/1611.01144/) (2016)
- [Deep Learning with Differential Privacy](https://mlsanity.com/paper/1607.00133/) (2016)
- [Membership Inference Attacks against Machine Learning Models](https://mlsanity.com/paper/1610.05820/) (2016)
- [Extracting Training Data from Large Language Models](https://mlsanity.com/paper/2012.07805/) (2020)
- [Adaptive Federated Optimization](https://mlsanity.com/paper/2003.00295/) (2020)
- [The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networks](https://mlsanity.com/paper/1802.08232/) (2018)
- [LEAF: A Benchmark for Federated Settings](https://mlsanity.com/paper/1812.01097/) (2018)
- [Inverting Gradients -- How easy is it to break privacy in federated learning?](https://mlsanity.com/paper/2003.14053/) (2020)
- [Evasion Attacks against Machine Learning at Test Time](https://mlsanity.com/paper/1708.06131/) (2017)
- [Renyi Differential Privacy](https://mlsanity.com/paper/1702.07476/) (2017)
- [Opacus: User-Friendly Differential Privacy Library in PyTorch](https://mlsanity.com/paper/2109.12298/) (2021)
- [See through Gradients: Image Batch Recovery via GradInversion](https://mlsanity.com/paper/2104.07586/) (2021)
- [The Composition Theorem for Differential Privacy](https://mlsanity.com/paper/1311.0776/) (2013)
- [White-box vs Black-box: Bayes Optimal Strategies for Membership Inference](https://mlsanity.com/paper/1908.11229/) (2019)
- [Subsampled R'enyi Differential Privacy and Analytical Moments Accountant](https://mlsanity.com/paper/1808.00087/) (2018)
- [Gradient-based Adversarial Attacks against Text Transformers](https://mlsanity.com/paper/2104.13733/) (2021)
- [Auditing Differentially Private Machine Learning: How Private is Private SGD?](https://mlsanity.com/paper/2006.07709/) (2020)
- [R'enyi Differential Privacy of the Sampled Gaussian Mechanism](https://mlsanity.com/paper/1908.10530/) (2019)
- [Adversary Instantiation: Lower Bounds for Differentially Private Machine Learning](https://mlsanity.com/paper/2101.04535/) (2021)
- [Numerical Composition of Differential Privacy](https://mlsanity.com/paper/2106.02848/) (2021)
- [Practical and Private (Deep) Learning without Sampling or Shuffling](https://mlsanity.com/paper/2103.00039/) (2021)
- [Mime: Mimicking Centralized Stochastic Algorithms in Federated Learning](https://mlsanity.com/paper/2008.03606/) (2020)
- [Reconstructing Training Data with Informed Adversaries](https://mlsanity.com/paper/2201.04845/) (2022)
- [When the Curious Abandon Honesty: Federated Learning Is Not Private](https://mlsanity.com/paper/2112.02918/) (2021)

## Built on by (most cited first, 24 of 24)

- [How to DP-fy ML: A Practical Guide to Machine Learning with Differential Privacy](https://mlsanity.com/paper/2303.00654/) (2023)
- [Privacy Auditing with One (1) Training Run](https://mlsanity.com/paper/2305.08846/) (2023)
- [One-shot Empirical Privacy Estimation for Federated Learning](https://mlsanity.com/paper/2302.03098/) (2023)
- [Gaussian Membership Inference Privacy](https://mlsanity.com/paper/2306.07273/) (2023)
- [Nearly Tight Black-Box Auditing of Differentially Private Machine Learning](https://mlsanity.com/paper/2405.14106/) (2024)
- [Unleashing the Power of Randomization in Auditing Differentially Private ML](https://mlsanity.com/paper/2305.18447/) (2023)
- [Tighter Privacy Auditing of DP-SGD in the Hidden State Threat Model](https://mlsanity.com/paper/2405.14457/) (2024)
- [The Elusive Pursuit of Reproducing PATE-GAN: Benchmarking, Auditing, Debugging](https://mlsanity.com/paper/2406.13985/) (2024)
- [Auditing Differential Privacy Guarantees Using Density Estimation](https://mlsanity.com/paper/2406.04827/) (2024)
- [To Shuffle or not to Shuffle: Auditing DP-SGD with Shuffling](https://mlsanity.com/paper/2411.10614/) (2024)
- [Optimizing Canaries for Privacy Auditing with Metagradient Descent](https://mlsanity.com/paper/2507.15836/) (2025)
- [The Hitchhiker's Guide to Efficient, End-to-End, and Tight DP Auditing](https://mlsanity.com/paper/2506.16666/) (2025)
- [Analyzing Inference Privacy Risks Through Gradients in Machine Learning](https://mlsanity.com/paper/2408.16913/) (2024)
- [Some Targets Are Harder to Identify than Others: Quantifying the Target-dependent Membership Leakage](https://mlsanity.com/paper/2402.10065/) (2024)
- [Epsilon*: Privacy Metric for Machine Learning Models](https://mlsanity.com/paper/2307.11280/) (2023)
- [On the Security and Privacy of Federated Learning: A Survey with Attacks, Defenses, Frameworks, Applications, and Future Directions](https://mlsanity.com/paper/2508.13730/) (2025)
- [MCMC for Bayesian estimation of Differential Privacy from Membership Inference Attacks](https://mlsanity.com/paper/2504.16683/) (2025)
- [Sequential Membership Inference Attacks](https://mlsanity.com/paper/2602.16596/) (2026)
- [Adversarial Sample-Based Approach for Tighter Privacy Auditing in Final Model-Only Scenarios](https://mlsanity.com/paper/2412.01756/) (2024)
- [Beyond Theoretical Bounds: Empirical Privacy Loss Calibration for Text Rewriting Under Local Differential Privacy](https://mlsanity.com/paper/2603.22968/) (2026)
- [Detectability in Diversity: Improved Canary Crafting for Privacy Auditing in One Run](https://mlsanity.com/paper/2605.27292/) (2026)
- [Advancing the State-of-the-Art in Empirical Privacy Auditing](https://mlsanity.com/paper/2606.10481/) (2026)
- [Let's Ask Gauss: Improved One-Run Privacy Auditing](https://mlsanity.com/paper/2606.12733/) (2026)
- [Canaries in the Bank: Auditing User-Level Privacy in Private Evolution](https://mlsanity.com/paper/2609.13499/) (2026)

## Abstract (arXiv)

Federated Learning (FL) is a setting for training machine learning models in distributed environments where the clients do not share their raw data but instead send model updates to a server. However, model updates can be subject to attacks and leak private information. Differential Privacy (DP) is a leading mitigation strategy which involves adding noise to clipped model updates, trading off performance for strong theoretical privacy guarantees. Previous work has shown that the threat model of DP is conservative and that the obtained guarantees may be vacuous or may overestimate information leakage in practice. In this paper, we aim to achieve a tighter measurement of the model exposure by considering a realistic threat model. We propose a novel method, CANIFE, that uses canaries - carefully crafted samples by a strong adversary to evaluate the empirical privacy of a training round. We apply this attack to vision models trained on CIFAR-10 and CelebA and to language models trained on Sent140 and Shakespeare. In particular, in realistic FL scenarios, we demonstrate that the empirical per-round epsilon obtained with CANIFE is 4-5x lower than the theoretical bound.