Amplitude-Varying Perturbation for Balancing Privacy and Utility in Federated Learning

Xin Yuan, Wei Ni, Ming Ding, Kang Wei, Jun Li, H. Vincent Poor

Federated Learning (FL) has emerged as a cornerstone for privacy-preserving distributed machine learning, allowing multiple clients to collaboratively train a model without sharing their raw data. However, the transmission of model updates still poses significant privacy risks, as sophisticated attackers can potentially reconstruct sensitive local information from these gradients. Differential Privacy (DP) is the standard defense, injecting noise into updates to provide mathematical privacy guarantees. Yet, traditional DP-FL faces a steep trade-off: excessive noise degrades model utility, while insufficient noise compromises privacy.

The Challenge of Constant Perturbation

Standard DP-FL implementations typically apply a constant level of Gaussian noise across all training rounds. This "one-size-fits-all" approach is often sub-optimal. In early training stages, high noise can lead to divergence, preventing the model from establishing a clear learning trajectory. Conversely, as training progresses and the cumulative privacy budget is consumed, maintaining high noise levels can cause the model to oscillate or diverge from the optimal solution.

Figure 1: Federated Learning architecture showing local training, model uploads, and the threat of an external attacker.

As illustrated in the system model above, the server aggregates local updates ($\tilde{\omega}_k$) to produce a global model ($\omega$). The goal is to protect these updates from an attacker while ensuring the final global model remains accurate.

Proposed Methodology: Time-Varying DP Perturbation

Researchers have proposed a novel Time-Varying DP Perturbation Mechanism to address these inefficiencies. Instead of fixed noise, the noise variance $\Theta(m)$ for the $m$-th round follows a geometric series:

$$\Theta(m) = \vartheta^{m-1}\sigma^2$$

Where $\sigma^2$ is the initial noise variance and $\vartheta$ is a scaling factor. By adjusting $\vartheta$, the system can either increase ($\vartheta > 1$) or decrease ($\vartheta < 1$) the noise amplitude over time. This flexibility allows the mechanism to be tailored to specific model architectures; for instance, empirical results suggest that decreasing noise ($\vartheta < 1$) often benefits Convolutional Neural Networks (CNNs), while increasing noise ($\vartheta > 1$) can be more effective for Support Vector Machines (SVMs).

Experimental Results and the "U-Shaped" Loss Curve

The mechanism was evaluated across several benchmarks, including MNIST, CIFAR-10, and Fashion-MNIST. A critical finding is the existence of a "U-shaped" loss curve in DP-FL. Unlike standard machine learning where more training generally leads to better results, DP-FL reaches a point of diminishing returns where cumulative noise begins to outweigh the benefits of further aggregation.

Figure 2: Impact of the scaling factor $\vartheta$ on (a) Loss function value and (b) Accuracy over the maximum number of global aggregation rounds (M).

As shown in the experimental data, there is an optimal number of aggregation rounds ($M^*$) that minimizes the loss and maximizes accuracy. The proposed time-varying mechanism consistently outperforms standard constant-noise Gaussian and Laplacian mechanisms. Specifically, by starting with smaller noise levels, the model can converge faster and reach higher peak accuracy before the privacy budget is exhausted.

Conclusion

By strategically varying noise amplitude, this new approach provides a more nuanced balance between privacy and utility. It not only achieves superior accuracy and faster convergence but also demonstrates robust defense against Membership Inference Attacks (MIA), reducing attacker success rates from over 99% to under 60%. Future work will focus on automating the selection of the scaling factor $\vartheta$ and extending theoretical convergence proofs to more complex architectures like Transformers.

Summary updated

Abstract

While preserving the privacy of federated learning (FL), differential privacy (DP) inevitably degrades the utility (i.e., accuracy) of FL due to model perturbations caused by DP noise added to model updates. Existing studies have considered exclusively noise with persistent root-mean-square amplitude and overlooked an opportunity of adjusting the amplitudes to alleviate the adverse effects of the noise. This paper presents a new DP perturbation mechanism with a time-varying noise amplitude to protect the privacy of FL and retain the capability of adjusting the learning performance. Specifically, we propose a geometric series form for the noise amplitude and reveal analytically the dependence of the series on the number of global aggregations and the <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$(\epsilon,\delta)$ </tex-math></inline-formula> -DP requirement. We derive an online refinement of the series to prevent FL from premature convergence resulting from excessive perturbation noise. Another important aspect is an upper bound developed for the loss function of a multi-layer perceptron (MLP) trained by FL running the new DP mechanism. Accordingly, the optimal number of global aggregations is obtained, balancing the learning and privacy. Extensive experiments are conducted using MLP, supporting vector machine, and convolutional neural network models on four public datasets. The contribution of the new DP mechanism to the convergence and accuracy of privacy-preserving FL is corroborated, compared to the state-of-the-art Gaussian noise mechanism with a persistent noise amplitude.
BibTeX
@article{yuan2023amplitude,
  author = {Xin Yuan and Wei Ni and Ming Ding and Kang Wei and Jun Li and H. Vincent Poor},
  title = {{Amplitude-Varying Perturbation for Balancing Privacy and Utility in Federated Learning}},
  journal = {IEEE Trans. Inf. Forensics Secur.},
  year = {2023},
  url = {https://openreview.net/forum?id=9ekz7Je4ggK},
}
Figure