More Like this

1. Gradient Inversion with Generative Image Prior

   Jeon, Jiwnoo; Kim, Jaechang; Lee, Kangwook; Oh, Sewoong; Ok, Jungseul (January 2021, Advances in neural information processing systems)

   Ranzato, M.; Beygelzimer, A.; Liang, P.S.; Vaughan, J.W.; Dauphin, Y. (Ed.)

   Federated Learning (FL) is a distributed learning framework, in which the local data never leaves clients’ devices to preserve privacy, and the server trains models on the data via accessing only the gradients of those local data. Without further privacy mechanisms such as differential privacy, this leaves the system vulnerable against an attacker who inverts those gradients to reveal clients’ sensitive data. However, a gradient is often insufficient to reconstruct the user data without any prior knowledge. By exploiting a generative model pretrained on the data distribution, we demonstrate that data privacy can be easily breached. Further, when such prior knowledge is unavailable, we investigate the possibility of learning the prior from a sequence of gradients seen in the process of FL training. We experimentally show that the prior in a form of generative model is learnable from iterative interactions in FL. Our findings demonstrate that additional mechanisms are necessary to prevent privacy leakage in FL. 

   more » « less
2. Federated Learning with Sparsification-Amplified Privacy and Adaptive Optimization

   https://doi.org/10.24963/ijcai.2021/202  

   Hu, Rui; Gong, Yanmin; Guo, Yuanxiong (August 2021, Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence)

   Federated learning (FL) enables distributed agents to collaboratively learn a centralized model without sharing their raw data with each other. However, data locality does not provide sufficient privacy protection, and it is desirable to facilitate FL with rigorous differential privacy (DP) guarantee. Existing DP mechanisms would introduce random noise with magnitude proportional to the model size, which can be quite large in deep neural networks. In this paper, we propose a new FL framework with sparsification-amplified privacy. Our approach integrates random sparsification with gradient perturbation on each agent to amplify privacy guarantee. Since sparsification would increase the number of communication rounds required to achieve a certain target accuracy, which is unfavorable for DP guarantee, we further introduce acceleration techniques to help reduce the privacy cost. We rigorously analyze the convergence of our approach and utilize Renyi DP to tightly account the end-to-end DP guarantee. Extensive experiments on benchmark datasets validate that our approach outperforms previous differentially-private FL approaches in both privacy guarantee and communication efficiency. 

   more » « less
3. GradCloak: Gradient Obfuscation for Privacy-Preserving Distributed Learning as a Service

   https://doi.org/10.1109/TSC.2026.3665393  

   Wei, Wenqi; Huang, Tiansheng; Hu, Sihao; Fan, Xinxin; Zhang, Rui; Zhou, Jingya; Liu, Ling (February 2026, IEEE Transactions on Services Computing)

   Gradient leakage attacks pose a significant privacy threat in distributed learning-as-a-service APIs. Existing literature on gradient leakage defense relies on gradient perturbation for preventing privacy leakage. However, determining where and how much to perturb the gradient offers different capabilities for preventing gradient leakage. This paper presents GradCloak, a principled approach to guiding gradient perturbation with theoretical robustness bounds in federated learning as a service, aiming to find the minimum required noise for simultaneously achieving privacy protection, competitive accuracy, and preventing gradient leakage attacks. The paper is organized into three major components. First, we formulate the gradient leakage threats and their adverse effect. We categorize the attack into two broad types: leakage during local training and leakage before global aggregation. Second, we investigate different gradient perturbation approaches. We analyze and compare these gradient perturbation methods, which are performed at the federated server, with those performed at the participating client(s). Third, we introduce three robustness properties of robust perturbation against gradient leakage threats, formulated by the anonymization bound for training data robustness, the perturbation bound for gradient robustness, and the distribution robustness bound for perturbed gradients. We conduct extensive evaluations on eight benchmark datasets to demonstrate that specific settings of gradient perturbation exist that best balance privacy, accuracy, and leakage prevention 

   more » « less
4. Communication Efficient Asynchronous Stochastic Gradient Descent

   https://doi.org/10.1109/INFOCOM55648.2025.11044686  

   Ahmed, Youssef; Ghosh, Arnob; Wang, Chih-Chun; Shroff, Ness B (May 2025, IEEE)

   In this paper, we address the challenges of asynchronous gradient descent in distributed learning environments, particularly focusing on addressing the challenges of stale gradients and the need for extensive communication resources. We develop a novel communication efficient framework that incorporates a gradient evaluation algorithm to assess and utilize delayed gradients based on their quality, ensuring efficient and effective model updates while significantly reducing communication overhead. Our proposed algorithm requires agents to only send the norm of the gradients rather than the computed gradient. The server then decides whether to accept the gradient if the ratio between the norm of the gradient and the distance between the global model parameter and the local model parameter exceeds a certain threshold. With the proper choice of the threshold, we show that the convergence rate achieves the same order as the synchronous stochastic gradient without depending on the staleness value unlike most of the existing works. Given the computational complexity of the initial algorithm, we introduce a simplified variant that prioritizes the practical applicability without compromising on the convergence rates. Our simulations demonstrate that our proposed algorithms outperform existing state-of-the-art methods, offering improved convergence rates, stability, accuracy, and resource consumption. 

   more » « less
5. Communication Efficient Asynchronous Stochastic Gradient Descent

   Ahmed, Y; Ghosh, A; Wang, C-C; Shroff, NB (May 2025, IEEE)

   In this paper, we address the challenges of asynchronous gradient descent in distributed learning environments, particularly focusing on addressing the challenges of stale gradients and the need for extensive communication resources. We develop a novel communication efficient framework that incorporates a gradient evaluation algorithm to assess and utilize delayed gradients based on their quality, ensuring efficient and effective model updates while significantly reducing communication overhead. Our proposed algorithm requires agents to only send the norm of the gradients rather than the computed gradient. The server then decides whether to accept the gradient if the ratio between the norm of the gradient and the distance between the global model parameter and the local model parameter exceeds a certain threshold. With the proper choice of the threshold, we show that the convergence rate achieves the same order as the synchronous stochastic gradient without depending on the staleness value unlike most of the existing works. Given the computational complexity of the initial algorithm, we introduce a simplified variant that prioritizes the practical applicability without compromising on the convergence rates. Our simulations demonstrate that our proposed algorithms outperform existing state-of-the-art methods, offering improved convergence rates, stability, accuracy, and resource consumption. 

   more » « less