The distributed (federated) LLM is an important method for co-training the domain-specific LLM using siloed data. However, maliciously stealing model parameters and data from the server or client side has become an urgent problem to be solved. In this paper, we propose a secure distributed LLM based on model slicing. In this case, we deploy the Trusted Execution Environment (TEE) on both the client and server side, and put the fine-tuned structure (LoRA or embedding of P-tuning v2) into the TEE. Then, secure communication is executed in the TEE and general environments through lightweight encryption. In order to further reduce the equipment cost as well as increase the model performance and accuracy, we propose a split fine-tuning scheme. In particular, we split the LLM by layers and place the latter layers in a server-side TEE (the client does not need a TEE). We then combine the proposed Sparsification Parameter Fine-tuning (SPF) with the LoRA part to improve the accuracy of the downstream task. Numerous experiments have shown that our method guarantees accuracy while maintaining security.
Carnegie Mellon University（卡内基梅隆大学）；Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）；Petuum Inc.（Petuum公司）；University of California, Berkeley（加州大学伯克利分校）
Enabling private inference is crucial for many cloud inference services that are based on Transformer models. However, existing private inference solutions can increase the inference latency by more than 60x or significantly compromise the inference quality. In this paper, we design the framework MPCFORMER as a practical solution, using Secure Multi-Party Computation (MPC) and Knowledge Distillation (KD). Through extensive evaluations, we show that MPCFORMER significantly speeds up Transformer inference in MPC settings while achieving similar ML performance to the input model. On the IMDb data…
Data integration and sharing maximally enhance the potential for novel and meaningful discoveries. However, it is a non-trivial task as integrating data from multiple sources can put sensitive information of study participants at risk. To address the privacy concern, we present a distributed Bayesian learning approach via Preconditioned Stochastic Gradient Langevin Dynamics with RMSprop, which combines differential privacy and homomorphic encryption in a harmonious manner while protecting private information. We applied the proposed secure and privacy-preserving distributed Bayesian learning a…
We design a scalable algorithm to privately generate location heatmaps over decentralized data from millions of user devices. It aims to ensure differential privacy before data becomes visible to a service provider while maintaining high data accuracy and minimizing resource consumption on users' devices. To achieve this, we revisit distributed differential privacy based on recent results in secure multiparty computation, and we design a scalable and adaptive distributed differential privacy approach for location analytics. Evaluation on public location datasets shows that this approach succes…
Computing the noisy sum of real-valued vectors is an important primitive in differentially private learning and statistics. In private federated learning applications, these vectors are held by client devices, leading to a distributed summation problem. Standard Secure Multiparty Computation (SMC) protocols for this problem are susceptible to poisoning attacks, where a client may have a large influence on the sum, without being detected. In this work, we propose a poisoning-robust private summation protocol in the multiple-server setting, recently studied in PRIO. We present a protocol for vec…
Coordinated Sciences Laboratory（协同科学实验室）；University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）
Federated learning systems that jointly preserve Byzantine robustness and privacy have remained an open problem. Robust aggregation, the standard defense for Byzantine attacks, generally requires server access to individual updates or nonlinear computation -- thus is incompatible with privacy-preserving methods such as secure aggregation via multiparty computation. To this end, we propose SHARE (Secure Hierarchical Robust Aggregation), a distributed learning framework designed to cryptographically preserve client update privacy and robustness to Byzantine adversaries simultaneously. The key id…
The University of British Columbia（不列颠哥伦比亚大学）；Shenzhen University（深圳大学）
The privacy concern exists when the central server has the copies of datasets. Hence, there is a paradigm shift for the learning networks to change from centralized in-cloud learning to distributed \mbox{on-device} learning. Benefit from the parallel computing, the on-device learning networks have a lower bandwidth requirement than the in-cloud learning networks. Moreover, the on-device learning networks also have several desirable characteristics such as privacy preserving and flexibility. However, the \mbox{on-device} learning networks are vulnerable to the malfunctioning terminals across th…
Distributed machine learning algorithms play a significant role in processing massive data sets over large networks. However, the increasing reliance on machine learning on information and communication technologies (ICTs) makes it inherently vulnerable to cyber threats. This work aims to develop secure distributed algorithms to protect the learning from data poisoning and network attacks. We establish a game-theoretic framework to capture the conflicting goals of a learner who uses distributed support vector machines (SVMs) and an attacker who is capable of modifying training data and labels.…
Université catholique de Louvain（天主教鲁汶大学）；Massachusetts Institute of Technology（麻省理工学院）
Distributed learning across a coalition of organizations allows the members of the coalition to train and share a model without sharing the data used to optimize this model. In this paper, we propose new secure architectures that guarantee preservation of data privacy, trustworthy sequence of iterative learning and equitable sharing of the learned model among each member of the coalition by using adequate encryption and blockchain mechanisms. We exemplify its deployment in the case of the distributed optimization of a deep learning convolutional neural network trained on medical images.
Especially in the Big Data era, the usage of different classification methods is increasing day by day. The success of these classification methods depends on the effectiveness of learning methods. Extreme learning machine (ELM) classification algorithm is a relatively new learning method built on feed-forward neural-network. ELM classification algorithm is a simple and fast method that can create a model from high-dimensional data sets. Traditional ELM learning algorithm implicitly assumes complete access to whole data set. This is a major privacy concern in most of cases. Sharing of private …
Federated Learning for Cross-Domain Data Privacy: A Distributed Approach to Secure Collaboration
Cornell University（康奈尔大学）；University of Minnesota（明尼苏达大学）；University of California, Los Angeles（加利福尼亚大学洛杉矶分校）；University of California, Berkeley（加利福尼亚大学伯克利分校）；Illinois Institute of Technology（伊利诺伊理工大学）
Microsoft（微软）；University of Washington Tacoma（华盛顿大学塔科马分校）；Universidade de Brasilia（巴西利亚大学）；Ghent University（根特大学）
Legal and ethical restrictions on accessing relevant data inhibit data science research in critical domains such as health, finance, and education. Synthetic data generation algorithms with privacy guarantees are emerging as a paradigm to break this data logjam. Existing approaches, however, assume that the data holders supply their raw data to a trusted curator, who uses it as fuel for synthetic data generation. This severely limits the applicability, as much of the valuable data in the world is locked up in silos, controlled by entities who cannot show their data to each other or a central a…
University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）
We consider distributed on-device learning with limited communication and security requirements. We propose a new robust distributed optimization algorithm with efficient communication and attack tolerance. The proposed algorithm has provable convergence and robustness under non-IID settings. Empirical results show that the proposed algorithm stabilizes the convergence and tolerates data poisoning on a small number of workers.
University of Pittsburgh（匹兹堡大学）；JD Finance America Corporation（京东金融美国公司）
Due to the rising privacy demand in data mining, Homomorphic Encryption (HE) is receiving more and more attention recently for its capability to do computations over the encrypted field. By using the HE technique, it is possible to securely outsource model learning to the not fully trustful but powerful public cloud computing environments. However, HE-based training scales badly because of the high computation complexity. It is still an open problem whether it is possible to apply HE to large-scale problems. In this paper, we propose a novel general distributed HE-based data mining framework t…
Distributed Support Vector Machines (DSVM) have been developed to solve large-scale classification problems in networked systems with a large number of sensors and control units. However, the systems become more vulnerable as detection and defense are increasingly difficult and expensive. This work aims to develop secure and resilient DSVM algorithms under adversarial environments in which an attacker can manipulate the training data to achieve his objective. We establish a game-theoretic framework to capture the conflicting interests between an adversary and a set of distributed data processi…
We consider training models on private data that are distributed across user devices. To ensure privacy, we add on-device noise and use secure aggregation so that only the noisy sum is revealed to the server. We present a comprehensive end-to-end system, which appropriately discretizes the data and adds discrete Gaussian noise before performing secure aggregation. We provide a novel privacy analysis for sums of discrete Gaussians and carefully analyze the effects of data quantization and modular summation arithmetic. Our theoretical guarantees highlight the complex tension between communicatio…
University Hospital Tübingen（图宾根大学医院）；University of Tübingen（图宾根大学）
The need for data privacy and security -- enforced through increasingly strict data protection regulations -- renders the use of healthcare data for machine learning difficult. In particular, the transfer of data between different hospitals is often not permissible and thus cross-site pooling of data not an option. The Personal Health Train (PHT) paradigm proposed within the GO-FAIR initiative implements an 'algorithm to the data' paradigm that ensures that distributed data can be accessed for analysis without transferring any sensitive data. We present PHT-meDIC, a productively deployed open-…
Software Competence Center Hagenberg（哈根贝格软件能力中心）；Faculty of Computer Science and Electrical Engineering, University of Rostock（罗斯托克大学计算机科学与电气工程学院）；Northwestern Polytechnical University（西北工业大学）
This study leverages the data representation capability of fuzzy based membership-mappings for practical secure distributed deep learning using fully homomorphic encryption. The impracticality issue of secure machine (deep) learning with fully homomorphic encrypted data, arising from large computational overhead, is addressed via applying fuzzy attributes. Fuzzy attributes are induced by globally convergent and robust variational membership-mappings based local deep models. Fuzzy attributes combine the local deep models in a robust and flexible manner such that the global model can be evaluate…
Broad Institute of MIT and Harvard（麻省理工学院与哈佛大学博德研究所）
We detail distributed algorithms for scalable, secure multiparty linear regression and feature selection at essentially the same speed as plaintext regression. While the core geometric ideas are simple, the recognition of their broad utility when combined is novel. Our scheme opens the door to efficient and secure genome-wide association studies across multiple biobanks.
Stevens Institute of Technology（史蒂文斯理工学院）；University of Carthage（迦太基大学）；Higher School of Communications of Tunis（突尼斯高等通信学院）
Internet-of-things (IoT) is perpetually revolutionizing our daily life and rapidly transforming physical objects into an ubiquitous connected ecosystem. Due to their massive deployment and moderate security levels, those devices face a lot of security, management, and control challenges. Their classical centralized architecture is still cloaking vulnerabilities and anomalies that can be exploited by hackers for spying, eavesdropping, and taking control of the network. In this paper, we propose to improve the IoT architecture with additional security features using Artificial Intelligence (AI) …
With the advent of big data era and the development of artificial intelligence and other technologies, data security and privacy protection have become more important. Recommendation systems have many applications in our society, but the model construction of recommendation systems is often inseparable from users' data. Especially for deep learning-based recommendation systems, due to the complexity of the model and the characteristics of deep learning itself, its training process not only requires long training time and abundant computational resources but also needs to use a large amount of …
Tencent（腾讯）；WeBank（微众银行）；University of Hong Kong（香港大学）；Xiamen University（厦门大学）；University of Ioannina（约阿尼纳大学）
Nonnegative matrix factorization (NMF) has been successfully applied in several data mining tasks. Recently, there is an increasing interest in the acceleration of NMF, due to its high cost on large matrices. On the other hand, the privacy issue of NMF over federated data is worthy of attention, since NMF is prevalently applied in image and text analysis which may involve leveraging privacy data (e.g, medical image and record) across several parties (e.g., hospitals). In this paper, we study the acceleration and security problems of distributed NMF. Firstly, we propose a distributed sketched a…
Decentralized learning is an efficient emerging paradigm for boosting the computing capability of multiple bounded computing agents. In the big data era, performing inference within the distributed and federated learning (DL and FL) frameworks, the central server needs to process a large amount of data while relying on various agents to perform multiple distributed training tasks. Considering the decentralized computing topology, privacy has become a first-class concern. Moreover, assuming limited information processing capability for the agents calls for a sophisticated \textit{privacy-preser…
MIPT（莫斯科物理技术学院）；Mila – Quebec AI Institute（米拉-魁北克人工智能研究所）；Yandex（扬德克斯）；HSE University（俄罗斯国立高等经济大学）
Many areas of deep learning benefit from using increasingly larger neural networks trained on public data, as is the case for pre-trained models for NLP and computer vision. Training such models requires a lot of computational resources (e.g., HPC clusters) that are not available to small research groups and independent researchers. One way to address it is for several smaller groups to pool their computational resources together and train a model that benefits all participants. Unfortunately, in this case, any participant can jeopardize the entire training run by sending incorrect updates, de…
