相关论文: Secure Quantized Training for Deep Learning

Secure multi-party computation (MPC) techniques can be used to provide data privacy when users query deep neural network (DNN) models hosted on a public cloud. State-of-the-art MPC techniques can be directly leveraged for DNN models that…

Deep learning models leak significant amounts of information about their training datasets. Previous work has investigated training models with differential privacy (DP) guarantees through adding DP noise to the gradients. However, such…

The high computation, memory, and power budgets of inferring convolutional neural networks (CNNs) are major bottlenecks of model deployment to edge computing platforms, e.g., mobile devices and IoT. Moreover, training CNNs is time and…

Unlike areas such as computer vision and speech recognition where convolutional and recurrent neural networks-based approaches have proven effective to the nature of the respective areas of application, deep learning (DL) still lacks a…

Predictions of certifiably robust classifiers remain constant in a neighborhood of a point, making them resilient to test-time attacks with a guarantee. In this work, we present a previously unrecognized threat to robust machine learning…

Deep neural networks (DNNs) have demonstrated their great potential in recent years, exceeding the per-formance of human experts in a wide range of applications. Due to their large sizes, however, compressiontechniques such as weight…

As Machine Learning (ML) is increasingly used in solving various tasks in real-world applications, it is crucial to ensure that ML algorithms are robust to any potential worst-case noises, adversarial attacks, and highly unusual situations…

Recent results show that deep neural networks achieve excellent performance even when, during training, weights are quantized and projected to a binary representation. Here, we show that this is just the tip of the iceberg: these same…

Most real-world applications that employ deep neural networks (DNNs) quantize them to low precision to reduce the compute needs. We present a method to improve the robustness of quantized DNNs to white-box adversarial attacks. We first…

We introduce a novel method for partial optimization of the connections in Deep Differentiable Logic Gate Networks (LGNs). Our training method utilizes a probability distribution over a subset of connections per gate input, selecting the…

Deep neural networks (DNNs) are vulnerable to malicious inputs crafted by an adversary to produce erroneous outputs. Works on securing neural networks against adversarial examples achieve high empirical robustness on simple datasets such as…

In this paper, we introduce a new concept called Artificial Special Intelligence by which Machine Learning models for the classification problem can be trained error-free, thus acquiring the capability of not making repeated mistakes. The…

Quantization is a popular way of increasing the speed and lowering the memory usage of Convolution Neural Networks (CNNs). When labelled training data is available, network weights and activations have successfully been quantized down to…

Quantized Neural Networks (QNNs) are often used to improve network efficiency during the inference phase, i.e. after the network has been trained. Extensive research in the field suggests many different quantization schemes. Still, the…

This paper presents an empirical study regarding training probabilistic neural networks using training objectives derived from PAC-Bayes bounds. In the context of probabilistic neural networks, the output of training is a probability…

As machine learning models, specifically neural networks, are becoming increasingly popular, there are concerns regarding their trustworthiness, specially in safety-critical applications, e.g. actions of an autonomous vehicle must be safe.…

Compressing large Neural Networks (NN) by quantizing the parameters, while maintaining the performance is highly desirable due to reduced memory and time complexity. In this work, we cast NN quantization as a discrete labelling problem, and…

We combine supervised learning with unsupervised learning in deep neural networks. The proposed model is trained to simultaneously minimize the sum of supervised and unsupervised cost functions by backpropagation, avoiding the need for…

Quantization of neural networks provides benefits of inference in less compute and memory requirements. Previous work in quantization lack two important aspects which this work provides. First almost all previous work in quantization used a…

Complex networks are ubiquitous to several Computer Science domains. Centrality measures are an important analysis mechanism to uncover vital elements of complex networks. However, these metrics have high computational costs and…