354 citations · 693 across the 36 of their papers we have counts for
36 papers
Chameleon: Adapting to Peer Images for Planting Durable Backdoors in Federated Learning
Yanbo Dai, Songze Li
In a federated learning (FL) system, distributed clients upload their local models to a central server to aggregate into a global model. Malicious clients may plant backdoors into…
Multi-Server Secure Aggregation with Unreliable Communication Links
Kai Liang, Songze Li, Ming Ding +1
In many distributed learning setups such as federated learning (FL), client nodes at the edge use individually collected data to compute local gradients and send them to a central…
Boosting Cross-task Transferability of Adversarial Patches with Visual Relations
Tony Ma, Songze Li, Yisong Xiao +1
The transferability of adversarial examples is a crucial aspect of evaluating the robustness of deep learning systems, particularly in black-box scenarios. Although several methods…
FedVS: Straggler-Resilient and Privacy-Preserving Vertical Federated Learning for Split Models
Songze Li, Duanyi Yao, Jin Liu
In a vertical federated learning (VFL) system consisting of a central server and many distributed clients, the training data are vertically partitioned such that different features…
Coded Distributed Computing for Hierarchical Multi-task Learning
Haoyang Hu, Songze Li, Minquan Cheng +1
In this paper, we consider a hierarchical distributed multi-task learning (MTL) system where distributed users wish to jointly learn different models orchestrated by a central serv…
Stochastic Coded Federated Learning: Theoretical Analysis and Incentive Mechanism Design
Yuchang Sun, Jiawei Shao, Yuyi Mao +2
Federated learning (FL) has achieved great success as a privacy-preserving distributed training paradigm, where many edge devices collaboratively train a machine learning model by…
DReS-FL: Dropout-Resilient Secure Federated Learning for Non-IID Clients via Secret Data Sharing
Jiawei Shao, Yuchang Sun, Songze Li +1
Federated learning (FL) strives to enable collaborative training of machine learning models without centrally collecting clients' private data. Different from centralized training,…
Secure Embedding Aggregation for Federated Representation Learning
Jiaxiang Tang, Jinbao Zhu, Songze Li +1
We consider a federated representation learning framework, where with the assistance of a central server, a group of distributed clients train collaboratively over their privat…
Secure Federated Clustering
Songze Li, Sizai Hou, Baturalp Buyukates +1
We consider a foundational unsupervised learning task of -means data clustering, in a federated learning (FL) setting consisting of a central server and many distributed clients…
Information-Theoretically Private Matrix Multiplication From MDS-Coded Storage
Jinbao Zhu, Songze Li, Jie Li
We study two problems of private matrix multiplication, over a distributed computing system consisting of a master node, and multiple servers that collectively store a family of pu…
SwiftAgg+: Achieving Asymptotically Optimal Communication Loads in Secure Aggregation for Federated Learning
Tayyebeh Jahani-Nezhad, Mohammad Ali Maddah-Ali, Songze Li +1
We propose SwiftAgg+, a novel secure aggregation protocol for federated learning systems, where a central server aggregates local models of distributed users, ea…
SwiftAgg: Communication-Efficient and Dropout-Resistant Secure Aggregation for Federated Learning with Worst-Case Security Guarantees
Tayyebeh Jahani-Nezhad, Mohammad Ali Maddah-Ali, Songze Li +1
We propose SwiftAgg, a novel secure aggregation protocol for federated learning systems, where a central server aggregates local models of distributed users, each of size ,…
Stochastic Coded Federated Learning with Convergence and Privacy Guarantees
Yuchang Sun, Jiawei Shao, Songze Li +2
Federated learning (FL) has attracted much attention as a privacy-preserving distributed machine learning framework, where many clients collaboratively train a machine learning mod…
A Systematic Approach towards Efficient Private Matrix Multiplication
Jinbao Zhu, Songze Li
We consider the problems of Private and Secure Matrix Multiplication (PSMM) and Fully Private Matrix Multiplication (FPMM), for which matrices privately selected by a master node a…
LightSecAgg: a Lightweight and Versatile Design for Secure Aggregation in Federated Learning
Jinhyun So, Chaoyang He, Chien-Sheng Yang +5
Secure model aggregation is a key component of federated learning (FL) that aims at protecting the privacy of each user's individual model while allowing for their global aggregati…
OmniLytics: A Blockchain-based Secure Data Market for Decentralized Machine Learning
Jiacheng Liang, Songze Li, Bochuan Cao +2
We propose OmniLytics, a blockchain-based secure data trading marketplace for machine learning applications. Utilizing OmniLytics, many distributed data owners can contribute their…
TaiJi: Longest Chain Availability with BFT Fast Confirmation
Songze Li, David Tse
Most state machine replication protocols are either based on the 40-years-old Byzantine Fault Tolerance (BFT) theory or the more recent Nakamoto's longest chain design. Longest cha…
Symmetric Private Polynomial Computation From Lagrange Encoding
Jinbao Zhu, Qifa Yan, Xiaohu Tang +1
The problem of -secure -colluding symmetric Private Polynomial Computation (PPC) from coded storage system with Byzantine and unresponsive servers is studied in this…
FedML: A Research Library and Benchmark for Federated Machine Learning
Chaoyang He, Songze Li, Jinhyun So +17
Federated learning (FL) is a rapidly growing research field in machine learning. However, existing FL libraries cannot adequately support diverse algorithmic development; inconsist…
Coded Merkle Tree: Solving Data Availability Attacks in Blockchains
Mingchao Yu, Saeid Sahraei, Songze Li +3
In this paper, we propose coded Merkle tree (CMT), a novel hash accumulator that offers a constant-cost protection against data availability attacks in blockchains, even if the maj…
Coded State Machine -- Scaling State Machine Execution under Byzantine Faults
Songze Li, Saeid Sahraei, Mingchao Yu +3
We introduce an information-theoretic framework, named Coded State Machine (CSM), to securely and efficiently execute multiple state machines on untrusted network nodes, some of wh…
GradiVeQ: Vector Quantization for Bandwidth-Efficient Gradient Aggregation in Distributed CNN Training
Mingchao Yu, Zhifeng Lin, Krishna Narra +6
Data parallelism can boost the training speed of convolutional neural networks (CNN), but could suffer from significant communication costs caused by gradient aggregation. To allev…
Pipe-SGD: A Decentralized Pipelined SGD Framework for Distributed Deep Net Training
Youjie Li, Mingchao Yu, Songze Li +3
Distributed training of deep nets is an important technique to address some of the present day computing challenges like memory consumption and computational demands. Classical dis…
PolyShard: Coded Sharding Achieves Linearly Scaling Efficiency and Security Simultaneously
Songze Li, Mingchao Yu, Chien-Sheng Yang +3
Today's blockchain designs suffer from a trilemma claiming that no blockchain system can simultaneously achieve decentralization, security, and performance scalability. For current…