How Does Noise Help Robustness? Explanation and Exploration under the Neural SDE Framework

Liu, Xuanqing; Xiao, Tesi; Si, Si; Cao, Qingqing; Kumar, Sanjiv; Hsieh, Cho‐Jui

doi:10.1109/cvpr42600.2020.00036

Cited by 32 publications

(21 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This method improves the robust generalization and decreases the trade-off between standard accuracy and adversarial robustness. Liu et al [151] proposed a new framework, termed Neural SDE which incorporates several regularization mechanisms based on random noise injection. This framework creates more robust models as achieves better generalization and is resistant to adversarial and non-adversarial perturbations.…”

Section: Benefits Of Adversarially Robust Modelsmentioning

confidence: 99%

A Survey on Adversarial Deep Learning Robustness in Medical Image Analysis

Apostolidis

Papakostas

2021

Electronics

View full text Add to dashboard Cite

In the past years, deep neural networks (DNN) have become popular in many disciplines such as computer vision (CV), natural language processing (NLP), etc. The evolution of hardware has helped researchers to develop many powerful Deep Learning (DL) models to face numerous challenging problems. One of the most important challenges in the CV area is Medical Image Analysis in which DL models process medical images—such as magnetic resonance imaging (MRI), X-ray, computed tomography (CT), etc.—using convolutional neural networks (CNN) for diagnosis or detection of several diseases. The proper function of these models can significantly upgrade the health systems. However, recent studies have shown that CNN models are vulnerable under adversarial attacks with imperceptible perturbations. In this paper, we summarize existing methods for adversarial attacks, detections and defenses on medical imaging. Finally, we show that many attacks, which are undetectable by the human eye, can degrade the performance of the models, significantly. Nevertheless, some effective defense and attack detection methods keep the models safe to an extent. We end with a discussion on the current state-of-the-art and future challenges.

show abstract

Section: Benefits Of Adversarially Robust Modelsmentioning

confidence: 99%

A Survey on Adversarial Deep Learning Robustness in Medical Image Analysis

Apostolidis

Papakostas

2021

Electronics

View full text Add to dashboard Cite

show abstract

“…Instead, standard deep learning optimization techniques could be used to train a parameterized differential function that can accurately describe the dynamics of a system. In the recent past, this has been used to infer the dynamics of various time-varying signals with practical applications [9,[213][214][215][216][217][218][219].…”

Section: Differential Equations With Deep Neural Networkmentioning

confidence: 99%

Generative Models of Brain Dynamics -- A review

Panahi¹,

Abrevaya²,

Gagnon-Audet³

et al. 2021

Preprint

View full text Add to dashboard Cite

The principled design and discovery of biologically-and physically-informed models of neuronal dynamics has been advancing since the mid-twentieth century. Recent developments in artificial intelligence (AI) have accelerated this progress. This review article gives a high-level overview of the approaches across different scales of organization and levels of abstraction. The studies covered in this paper include fundamental models in computational neuroscience, nonlinear dynamics, datadriven methods, as well as emergent practices. While not all of these models span the intersection of neuroscience, AI, and system dynamics, all of them do or can work in tandem as generative models, which, as we argue, provide superior properties for the analysis of neuroscientific data. We discuss the limitations and unique dynamical traits of brain data and the complementary need for hypothesisand data-driven modeling. By way of conclusion, we present several hybrid generative models from recent literature in scientific machine learning, which can be efficiently deployed to yield interpretable models of neural dynamics.

show abstract

“…This approach lead to a series of works [10,5,6] by addressing the issues in [4]. Stochastic variants of NODE [16,20] were also proposed but the evaluation of their proposed methods are restricted to simple architectures. To achieve similar generalization performance compared with Resnet architecture, [10] proposed a modified adjoint approach which address the issue of computing incorrect gradients in [4].…”

Section: Related Workmentioning

confidence: 99%

Improving Robustness and Uncertainty Modelling in Neural Ordinary Differential Equations

Anumasa,

Srijith

2021

Preprint

View full text Add to dashboard Cite

Deep learning models such as Resnets have resulted in state-of-the-art accuracy in many computer vision problems. Neural ordinary differential equations (NODE) provides a continuous depth generalization of Resnets and overcome drawbacks of Resnet such as model selection and parameter complexity. Though NODE is more robust than Resnet, we find that NODE based architectures are still far away from providing robustness and uncertainty handling required for many computer vision problems. We propose novel NODE models which address these drawbacks. In particular, we propose Gaussian processes (GPs) to model the fully connected neural networks in NODE (NODE-GP) to improve robustness and uncertainty handling capabilities of NODE. The proposed model is flexible to accommodate different NODE architectures, and further improves the model selection capabilities in NODEs. We also find that numerical techniques play an important role in modelling NODE robustness, and propose to use different numerical techniques to improve NODE robustness. We demonstrate the superior robustness and uncertainty handling capabilities of proposed models on adversarial attacks and out-ofdistribution experiments for the image classification tasks.

show abstract

How Does Noise Help Robustness? Explanation and Exploration under the Neural SDE Framework

Cited by 32 publications

References 7 publications

A Survey on Adversarial Deep Learning Robustness in Medical Image Analysis

A Survey on Adversarial Deep Learning Robustness in Medical Image Analysis

Generative Models of Brain Dynamics -- A review

Improving Robustness and Uncertainty Modelling in Neural Ordinary Differential Equations

Contact Info

Product

Resources

About