Search Results for author:
Found 24 papers, 8 papers with code
StATIK: Structure and Text for Inductive Knowledge Graph Completion
Knowledge graphs (KGs) often represent knowledge bases that are incomplete.
Differentially Private Next-Token Prediction of Large Language Models
Ensuring the privacy of Large Language Models (LLMs) is becoming increasingly important.
Edge Private Graph Neural Networks with Singular Value Perturbation
Eclipse adds noise to the low-rank singular values instead of the entire graph, thereby preserving the graph privacy while still maintaining enough of the graph structure to maintain model utility.
Ethos: Rectifying Language Models in Orthogonal Parameter Space
Evaluations show Ethos is more effective in removing undesired knowledge and maintaining the overall model performance compared to current task arithmetic methods.
Differentially Private Knowledge Distillation via Synthetic Text Generation
However, the increasing urgency of data privacy requires LLMs to train with Differential Privacy (DP) on private data.
Data Leakage via Access Patterns of Sparse Features in Deep Learning-based Recommendation Systems
This paper explores the private information that may be learned by tracking a recommendation model's sparse feature access patterns.
MPC-Pipe: an Efficient Pipeline Scheme for Secure Multi-party Machine Learning Inference
Multi-party computing (MPC) has been gaining popularity over the past years as a secure computing model, particularly for machine learning (ML) inference.
DarKnight: An Accelerated Framework for Privacy and Integrity Preserving Deep Learning Using Trusted Hardware
DarKnight relies on cooperative execution between trusted execution environments (TEE) and accelerators, where the TEE provides privacy and integrity verification, while accelerators perform the bulk of the linear algebraic computation to optimize the performance.
Attribute Inference Attack of Speech Emotion Recognition in Federated Learning Settings
To assess the information leakage of SER systems trained using FL, we propose an attribute inference attack framework that infers sensitive attribute information of the clients from shared gradients or model parameters, corresponding to the FedSGD and the FedAvg training algorithms, respectively.
Adaptive Verifiable Coded Computing: Towards Fast, Secure and Private Distributed Machine Learning
Much of the overhead in prior schemes comes from the fact that they tightly couple coding for all three problems into a single framework.
SpreadGNN: Serverless Multi-task Federated Learning for Graph Neural Networks
This work proposes SpreadGNN, a novel multi-task federated training framework capable of operating in the presence of partial labels and absence of a central server for the first time in the literature.
Byzantine-Robust and Privacy-Preserving Framework for FedML
This learning setting presents, among others, two unique challenges: how to protect privacy of the clients' data during training, and how to ensure integrity of the trained model.
Privacy and Integrity Preserving Training Using Trusted Hardware
Privacy and security-related concerns are growing as machine learning reaches diverse application domains.
FedGraphNN: A Federated Learning System and Benchmark for Graph Neural Networks
FedGraphNN is built on a unified formulation of graph FL and contains a wide range of datasets from different domains, popular GNN models, and FL algorithms, with secure and efficient system support.
Distributed Training of Graph Convolutional Networks using Subgraph Approximation
Modern machine learning techniques are successfully being adapted to data modeled as graphs.
Check-N-Run: A Checkpointing System for Training Deep Learning Recommendation Models
While Check-N-Run is applicable to long running ML jobs, we focus on checkpointing recommendation models which are currently the largest ML models with Terabytes of model size.
Group Knowledge Transfer: Federated Learning of Large CNNs at the Edge
However, the large model size impedes training on resource-constrained edge devices.
FedML: A Research Library and Benchmark for Federated Machine Learning
Federated learning (FL) is a rapidly growing research field in machine learning.
Towards Non-I.I.D. and Invisible Data with FedNAS: Federated Deep Learning via Neural Architecture Search
Federated Learning (FL) has been proved to be an effective learning framework when data cannot be centralized due to privacy, communication costs, and regulatory restrictions.
Privacy-Preserving Inference in Machine Learning Services Using Trusted Execution Environments
However, the overhead of blinding and unblinding the data is a limiting factor to scalability.
Train Where the Data is: A Case for Bandwidth Efficient Coded Training
Most of the model training is performed on high performance compute nodes and the training data is stored near these nodes for faster training.
Collage Inference: Achieving low tail latency during distributed image classification using coded redundancy models
In this work, we argue that MLaaS platforms also provide unique opportunities to cut the cost of redundancy.
Collage Inference: Using Coded Redundancy for Low Variance Distributed Image Classification
Deploying the collage-cnn models in the cloud, we demonstrate that the 99th percentile tail latency of inference can be reduced by 1. 2x to 2x compared to replication based approaches while providing high accuracy.
GradiVeQ: Vector Quantization for Bandwidth-Efficient Gradient Aggregation in Distributed CNN Training
Data parallelism can boost the training speed of convolutional neural networks (CNN), but could suffer from significant communication costs caused by gradient aggregation.
