Search

Transfer learning via fine-tuning pre-trained transformer models has gained significant success in delivering state-of-the-art results across various NLP tasks. In the absence of centralized data, Federated Learning (FL) can benefit from distributed and private data of the FL edge clients for fine-tuning. However, due to the limited communication, computation, and storage capabilities of edge devices and the huge sizes of popular transformer models, efficient fine-tuning is crucial to make federated training feasible. This work explores the opportunities and challenges associated with applying parameter efficient fine-tuning (PEFT) methods in different FL settings for language tasks. Specifically, our investigation reveals that as the data across users becomes more diverse, the gap between fully fine-tuning the model and employing PEFT methods widens. To bridge this performance gap, we propose a method called SLoRA, which overcomes the key limitations of LoRA in high heterogeneous data scenarios through a novel data-driven initialization technique. Our experimental results demonstrate that SLoRA achieves performance comparable to full fine-tuning, with significant sparse updates with approximately $\sim 1\%$ density while reducing training time by up to $90\%$.

Secure aggregation promises a heightened level of privacy in federated learning, maintaining that a server only has access to a decrypted aggregate update. Within this setting, linear layer leakage methods are the only data reconstruction attacks able to scale and achieve a high leakage rate regardless of the number of clients or batch size. This is done through increasing the size of an injected fully-connected (FC) layer. However, this results in a resource overhead which grows larger with an increasing number of clients. We show that this resource overhead is caused by an incorrect perspective in all prior work that treats an attack on an aggregate update in the same way as an individual update with a larger batch size. Instead, by attacking the update from the perspective that aggregation is combining multiple individual updates, this allows the application of sparsity to alleviate resource overhead. We show that the use of sparsity can decrease the model size overhead by over 327$\times$ and the computation time by 3.34$\times$ compared to SOTA while maintaining equivalent total leakage rate, 77% even with $1000$ clients in aggregation., Comment: Accepted to CVPR 2023

Federated learning was introduced to enable machine learning over large decentralized datasets while promising privacy by eliminating the need for data sharing. Despite this, prior work has shown that shared gradients often contain private information and attackers can gain knowledge either through malicious modification of the architecture and parameters or by using optimization to approximate user data from the shared gradients. However, prior data reconstruction attacks have been limited in setting and scale, as most works target FedSGD and limit the attack to single-client gradients. Many of these attacks fail in the more practical setting of FedAVG or if updates are aggregated together using secure aggregation. Data reconstruction becomes significantly more difficult, resulting in limited attack scale and/or decreased reconstruction quality. When both FedAVG and secure aggregation are used, there is no current method that is able to attack multiple clients concurrently in a federated learning setting. In this work we introduce LOKI, an attack that overcomes previous limitations and also breaks the anonymity of aggregation as the leaked data is identifiable and directly tied back to the clients they come from. Our design sends clients customized convolutional parameters, and the weight gradients of data points between clients remain separate even through aggregation. With FedAVG and aggregation across 100 clients, prior work can leak less than 1% of images on MNIST, CIFAR-100, and Tiny ImageNet. Using only a single training round, LOKI is able to leak 76-86% of all data samples., Comment: To appear in the IEEE Symposium on Security & Privacy (S&P) 2024

Federated analytics (FA) is a privacy-preserving framework for computing data analytics over multiple remote parties (e.g., mobile devices) or silo-ed institutional entities (e.g., hospitals, banks) without sharing the data among parties. Motivated by the practical use cases of federated analytics, we follow a systematic discussion on federated analytics in this article. In particular, we discuss the unique characteristics of federated analytics and how it differs from federated learning. We also explore a wide range of FA queries and discuss various existing solutions and potential use case applications for different FA queries., Comment: To appear in APSIPA Transactions on Signal and Information Processing, Volume 12, Issue 1

Federated learning (FL) has attracted growing interest for enabling privacy-preserving machine learning on data stored at multiple users while avoiding moving the data off-device. However, while data never leaves users' devices, privacy still cannot be guaranteed since significant computations on users' training data are shared in the form of trained local models. These local models have recently been shown to pose a substantial privacy threat through different privacy attacks such as model inversion attacks. As a remedy, Secure Aggregation (SA) has been developed as a framework to preserve privacy in FL, by guaranteeing the server can only learn the global aggregated model update but not the individual model updates. While SA ensures no additional information is leaked about the individual model update beyond the aggregated model update, there are no formal guarantees on how much privacy FL with SA can actually offer; as information about the individual dataset can still potentially leak through the aggregated model computed at the server. In this work, we perform a first analysis of the formal privacy guarantees for FL with SA. Specifically, we use Mutual Information (MI) as a quantification metric and derive upper bounds on how much information about each user's dataset can leak through the aggregated model update. When using the FedSGD aggregation algorithm, our theoretical bounds show that the amount of privacy leakage reduces linearly with the number of users participating in FL with SA. To validate our theoretical bounds, we use an MI Neural Estimator to empirically evaluate the privacy leakage under different FL setups on both the MNIST and CIFAR10 datasets. Our experiments verify our theoretical bounds for FedSGD, which show a reduction in privacy leakage as the number of users and local batch size grow, and an increase in privacy leakage with the number of training rounds., Comment: Accepted to appear in Proceedings on Privacy Enhancing Technologies (PoPETs) 2023

Detection and mitigation of Byzantine behaviors in a decentralized learning setting is a daunting task, especially when the data distribution at the users is heterogeneous. As our main contribution, we propose Basil, a fast and computationally efficient Byzantine robust algorithm for decentralized training systems, which leverages a novel sequential, memory assisted and performance-based criteria for training over a logical ring while filtering the Byzantine users. In the IID dataset distribution setting, we provide the theoretical convergence guarantees of Basil, demonstrating its linear convergence rate. Furthermore, for the IID setting, we experimentally demonstrate that Basil is robust to various Byzantine attacks, including the strong Hidden attack, while providing up to ${\sim}16 \%$ higher test accuracy over the state-of-the-art Byzantine-resilient decentralized learning approach. Additionally, we generalize Basil to the non-IID dataset distribution setting by proposing Anonymous Cyclic Data Sharing (ACDS), a technique that allows each node to anonymously share a random fraction of its local non-sensitive dataset (e.g., landmarks images) with all other nodes. We demonstrate that Basil alongside ACDS with only $5\%$ data sharing provides effective toleration of Byzantine nodes, unlike the state-of-the-art Byzantine robust algorithm that completely fails in the heterogeneous data setting. Finally, to reduce the overall latency of Basil resulting from its sequential implementation over the logical ring, we propose Basil+. In particular, Basil+ provides scalability by enabling Byzantine-robust parallel training across groups of logical rings, and at the same time, it retains the performance gains of Basil due to sequential training within each group. Furthermore, we experimentally demonstrate the scalability gains of Basil+ through different sets of experiments., Comment: Final version was accepted for publication in IEEE JSAC Series on Machine Learning for Communications and Networks. A part of the work was presented at the NeurIPS Workshop on Privacy in Machine Learning, 2021

Secure model aggregation across many users is a key component of federated learning systems. The state-of-the-art protocols for secure model aggregation, which are based on additive masking, require all users to quantize their model updates to the same level of quantization. This severely degrades their performance due to lack of adaptation to available bandwidth at different users. We propose three schemes that allow secure model aggregation while using heterogeneous quantization. This enables the users to adjust their quantization proportional to their available bandwidth, which can provide a substantially better trade-off between the accuracy of training and the communication time. The proposed schemes are based on a grouping strategy by partitioning the network into groups, and partitioning the local model updates of users into segments. Instead of applying aggregation protocol to the entire local model update vector, it is applied on segments with specific coordination between users. We theoretically evaluate the quantization error for our schemes, and also demonstrate how our schemes can be utilized to overcome Byzantine users.