Related papers: Securing Neural Networks with Knapsack Optimizatio…
Tiny deep learning on microcontroller units (MCUs) is challenging due to the limited memory size. We find that the memory bottleneck is due to the imbalanced memory distribution in convolutional neural network (CNN) designs: the first…
Point cloud segmentation and classification are some of the primary tasks in 3D computer vision with applications ranging from augmented reality to robotics. However, processing point clouds using deep learning-based algorithms is quite…
We present a novel layerwise optimization algorithm for the learning objective of Piecewise-Linear Convolutional Neural Networks (PL-CNNs), a large class of convolutional neural networks. Specifically, PL-CNNs employ piecewise linear…
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…
Neural networks have demonstrated a wide range of successes, but their ``black box" nature raises concerns about transparency and reliability. Previous research on ReLU networks has sought to unwrap these networks into linear models based…
It has become mainstream in computer vision and other machine learning domains to reuse backbone networks pre-trained on large datasets as preprocessors. Typically, the last layer is replaced by a shallow learning machine of sorts; the…
Recurrent neural networks (RNNs) have recently achieved remarkable successes in a number of applications. However, the huge sizes and computational burden of these models make it difficult for their deployment on edge devices. A practically…
More and more evidence has shown that strengthening layer interactions can enhance the representation power of a deep neural network, while self-attention excels at learning interdependencies by retrieving query-activated information.…
Neural networks have shown tremendous potential for reconstructing high-resolution images in inverse problems. The non-convex and opaque nature of neural networks, however, hinders their utility in sensitive applications such as medical…
We argue that the machine learning problem of model extraction is actually a cryptanalytic problem in disguise, and should be studied as such. Given oracle access to a neural network, we introduce a differential attack that can efficiently…
Capsule networks are a type of neural network that have recently gained increased popularity. They consist of groups of neurons, called capsules, which encode properties of objects or object parts. The connections between capsules encrypt…
Convolutional Neural Networks (CNNs) are the state of the art solution for many computer vision problems, and many researchers have explored optimized implementations. Most implementations heuristically block the computation to deal with…
Recent work using Fully Homomorphic Encryption (FHE) has made non-interactive privacy-preserving inference of deep Convolutional Neural Networks (CNN) possible. However, the performance of these methods remain limited by their heavy…
Deep neural networks often lack the safety and robustness guarantees needed to be deployed in safety critical systems. Formal verification techniques can be used to prove input-output safety properties of networks, but when properties are…
Pursuing the precise details of super-resolution images is challenging for single-image super-resolution tasks. This paper presents a single-image super-resolution network with hairline details (termed NLCUnet), including three core…
Recently, theoretical analyses of deep neural networks have broadly focused on two directions: 1) Providing insight into neural network training by SGD in the limit of infinite hidden-layer width and infinitesimally small learning rate…
Capsule Networks (CapsNets) is a machine learning architecture proposed to overcome some of the shortcomings of convolutional neural networks (CNNs). However, CapsNets have mainly outperformed CNNs in datasets where images are small and/or…
Recurrent Neural Networks (RNNs) are used in state-of-the-art models in domains such as speech recognition, machine translation, and language modelling. Sparsity is a technique to reduce compute and memory requirements of deep learning…
Privacy-preserving machine learning (PPML) aims at enabling machine learning (ML) algorithms to be used on sensitive data. We contribute to this line of research by proposing a framework that allows efficient and secure evaluation of…
Replacing non-polynomial functions (e.g., non-linear activation functions such as ReLU) in a neural network with their polynomial approximations is a standard practice in privacy-preserving machine learning. The resulting neural network,…