相关论文: Secure Evaluation of Quantized Neural Networks

Machine learning has been revolutionizing our world over the last few years and is also increasingly exploited in several areas of physics, including quantum dynamics and control.The need for a framework that brings together machine…

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…

The success of Deep Learning and its potential use in many safety-critical applications has motivated research on formal verification of Neural Network (NN) models. Despite the reputation of learned NN models to behave as black boxes and…

With the growing concern of AI safety, there is a need to trust the computations done by machine learning (ML) models. Blockchain technology, known for recording data and running computations transparently and in a tamper-proof manner, can…

Reinforcement learning policies are typically represented by black-box neural networks, which are non-interpretable and not well-suited for safety-critical domains. To address both of these issues, we propose constrained normalizing flow…

In deep learning applications, robustness measures the ability of neural models that handle slight changes in input data, which could lead to potential safety hazards, especially in safety-critical applications. Pre-deployment assessment of…

Recursive neural networks have widely been used by researchers to handle applications with recursively or hierarchically structured data. However, embedded control flow deep learning frameworks such as TensorFlow, Theano, Caffe2, and MXNet…

Cryptographically secure neural network inference typically relies on secure computing techniques such as Secure Multi-Party Computation (MPC), enabling cloud servers to process client inputs without decrypting them. Although prior…

If Uncertainty Quantification (UQ) is crucial to achieve trustworthy Machine Learning (ML), most UQ methods suffer from disparate and inconsistent evaluation protocols. We claim this inconsistency results from the unclear requirements the…

Recent developments in Machine Learning and Deep Learning depend heavily on cloud computing and specialized hardware, such as GPUs and TPUs. This forces those using those models to trust private data to cloud servers. Such scenario has…

In nuclear engineering, modeling and simulations (M&Ss) are widely applied to support risk-informed safety analysis. Since nuclear safety analysis has important implications, a convincing validation process is needed to assess simulation…

Recent research implies that training and inference of deep neural networks (DNN) can be computed with low precision numerical representations of the training/test data, weights and gradients without a general loss in accuracy. The benefit…

Trustworthy machine learning is driving a large number of ML community works in order to improve ML acceptance and adoption. The main aspect of trustworthy machine learning are the followings: fairness, uncertainty, robustness,…

Neural networks (NNs) are currently changing the computational paradigm on how to combine data with mathematical laws in physics and engineering in a profound way, tackling challenging inverse and ill-posed problems not solvable with…

Most supervised machine learning tasks are subject to irreducible prediction errors. Probabilistic predictive models address this limitation by providing probability distributions that represent a belief over plausible targets, rather than…

While distributed algorithms provide advantages for the control of complex large-scale systems by requiring a lower local computational load and less local memory, it is a challenging task to design high-performance distributed control…

Quantifying the robustness of neural networks or verifying their safety properties against input uncertainties or adversarial attacks have become an important research area in learning-enabled systems. Most results concentrate around the…

In several settings of practical interest, two parties seek to collaboratively perform inference on their private data using a public machine learning model. For instance, several hospitals might wish to share patient medical records for…

When we rely on deep-learned models for robotic perception, we must recognize that these models may behave unreliably on inputs dissimilar from the training data, compromising the closed-loop system's safety. This raises fundamental…

With the increasing prevalence of encrypted network traffic, cyber security analysts have been turning to machine learning (ML) techniques to elucidate the traffic on their networks. However, ML models can become stale as new traffic…