相关论文: Secure Quantized Training for Deep Learning

Adversarial examples pose a security threat to many critical systems built on neural networks (such as face recognition systems, and self-driving cars). While many methods have been proposed to build robust models, how to build certifiably…

Recent work has explored reduced numerical precision for parameters, activations, and gradients during neural network training as a way to reduce the computational cost of training (Na & Mukhopadhyay, 2016) (Courbariaux et al., 2014). We…

Secure multiparty computation (MPC) allows data owners to train machine learning models on combined data while keeping the underlying training data private. The MPC threat model either considers an adversary who passively corrupts some…

In this work, we present an efficient secure multi-party computation MPC protocol that provides strong security guarantees in settings with dishonest majority of participants who may behave arbitrarily. Unlike the popular MPC implementation…

We propose a principled framework that combines adversarial training and provable robustness verification for training certifiably robust neural networks. We formulate the training problem as a joint optimization problem with both empirical…

Existing work on privacy-preserving machine learning with Secure Multiparty Computation (MPC) is almost exclusively focused on model training and on inference with trained models, thereby overlooking the important data pre-processing stage.…

Secure Multi-Party Computation (MPC) is an area of cryptography that enables computation on sensitive data from multiple sources while maintaining privacy guarantees. However, theoretical MPC protocols often do not scale efficiently to…

Tensor networks are efficient representations of high-dimensional tensors which have been very successful for physics and mathematics applications. We demonstrate how algorithms for optimizing such networks can be adapted to supervised…

While neural networks have achieved high accuracy on standard image classification benchmarks, their accuracy drops to nearly zero in the presence of small adversarial perturbations to test inputs. Defenses based on regularization and…

Formal verification provides critical security assurances for neural networks, yet its practical application suffers from the long verification time. This work introduces a novel method for training verification-friendly neural networks,…

Deep clustering algorithms combine representation learning and clustering by jointly optimizing a clustering loss and a non-clustering loss. In such methods, a deep neural network is used for representation learning together with a…

We investigate two questions in this paper: First, we ask to what extent "MPC friendly" models are already supported by major Machine Learning frameworks such as TensorFlow or PyTorch. Prior works provide protocols that only work on…

Classifying hand-written digits and letters has taken a big leap with the introduction of ConvNets. However, on very constrained hardware the time necessary to train such models would be high. Our main contribution is twofold. First, we…

Deep Learning has revolutionized the fields of computer vision, natural language understanding, speech recognition, information retrieval and more. Many techniques have evolved over the past decade that made models lighter, faster, and…

Training a machine learning model over an encrypted dataset is an existing promising approach to address the privacy-preserving machine learning task, however, it is extremely challenging to efficiently train a deep neural network (DNN)…

In this work, we investigate the use of sparsity-inducing regularizers during training of Convolution Neural Networks (CNNs). These regularizers encourage that fewer connections in the convolution and fully connected layers take non-zero…

We present a fast, fully parameterizable GPU implementation of Convolutional Neural Network variants. Our feature extractors are neither carefully designed nor pre-wired, but rather learned in a supervised way. Our deep hierarchical…

This paper presents a novel approach to training neural networks with formal safety guarantees using semidefinite programming (SDP) for verification. Our method focuses on verifying safety over large, high-dimensional input regions,…

Large-scale convolutional neural networks (CNNs) suffer from very long training times, spanning from hours to weeks, limiting the productivity and experimentation of deep learning practitioners. As networks grow in size and complexity,…

Deep learning training involves a large number of operations, which are dominated by high dimensionality Matrix-Vector Multiplies (MVMs). This has motivated hardware accelerators to enhance compute efficiency, but where data movement and…