Search Results for author:
Found 12 papers, 3 papers with code
LazyDP: Co-Designing Algorithm-Software for Scalable Training of Differentially Private Recommendation Models
Differential privacy (DP) is widely being employed in the industry as a practical standard for privacy protection.
Approximating ReLU on a Reduced Ring for Efficient MPC-based Private Inference
Secure multi-party computation (MPC) allows users to offload machine learning inference on untrusted servers without having to share their privacy-sensitive data.
Information Flow Control in Machine Learning through Modular Model Architecture
In today's machine learning (ML) models, any part of the training data can affect its output.
GPU-based Private Information Retrieval for On-Device Machine Learning Inference
Together, for various on-device ML applications such as recommendation and language modeling, our system on a single V100 GPU can serve up to $100, 000$ queries per second -- a $>100 \times$ throughput improvement over a CPU-based baseline -- while maintaining model accuracy.
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.
Cocktail Party Attack: Breaking Aggregation-Based Privacy in Federated Learning using Independent Component Analysis
Federated learning (FL) aims to perform privacy-preserving machine learning on distributed data held by multiple data owners.
Structured Pruning is All You Need for Pruning CNNs at Initialization
In addition, since PreCropping compresses CNNs at initialization, the computational and memory costs of CNNs are reduced for both training and inference on commodity hardware.
BulletTrain: Accelerating Robust Neural Network Training via Boundary Example Mining
Neural network robustness has become a central topic in machine learning in recent years.
GuardNN: Secure Accelerator Architecture for Privacy-Preserving Deep Learning
This paper proposes GuardNN, a secure DNN accelerator that provides hardware-based protection for user data and model parameters even in an untrusted environment.
MGX: Near-Zero Overhead Memory Protection for Data-Intensive Accelerators
This paper introduces MGX, a near-zero overhead memory protection scheme for hardware accelerators.
Precision Gating: Improving Neural Network Efficiency with Dynamic Dual-Precision Activations
The proposed approach is applicable to a variety of DNN architectures and significantly reduces the computational cost of DNN execution with almost no accuracy loss.
Channel Gating Neural Networks
Combining our method with knowledge distillation reduces the compute cost of ResNet-18 by 2. 6$\times$ without accuracy drop on ImageNet.
