skip to main content

Attention:

The NSF Public Access Repository (NSF-PAR) system and access will be unavailable from 11:00 PM ET on Thursday, June 13 until 2:00 AM ET on Friday, June 14 due to maintenance. We apologize for the inconvenience.


Title: Robustness Analysis for Convolutional Neural Networks with Uncertainty Quantification
This paper presents a novel framework for training convolutional neural networks (CNNs) to quantify the impact of gradual and abrupt uncertainties in the form of adversarial attacks. Uncertainty quantification is achieved by combining the CNN with a Gaussian process (GP) classifier algorithm. The variance of the GP quantifies the impact on the uncertainties and especially their effect on the object classification tasks. Learning from uncertainty provides the proposed CNN-GP framework with flexibility, reliability and robustness to adversarial attacks. The proposed approach includes training the network under noisy conditions. This is accomplished by comparing predictions with classification labels via the Kullback-Leibler divergence, Wasserstein distance and maximum correntropy. The network performance is tested on the classical MNIST, Fashion-MNIST, CIFAR10 and CIFAR 100 datasets. Further tests on robustness to both black-box and white-box attacks are also carried out for MNIST. The results show that the testing accuracy improves for networks that backpropogate uncertainty as compared to methods that do not quantify the impact of uncertainties. A comparison with a state-of-art Monte Carlo dropout method is also presented and the outperformance of the CNN-GP framework with respect to reliability and computational efficiency is demonstrated.  more » « less
Award ID(s):
1903466
NSF-PAR ID:
10259931
Author(s) / Creator(s):
Date Published:
Journal Name:
Proc. of the International Forum on Signal Processing
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. The remarkable success of the Transformer model in Natural Language Processing (NLP) is increasingly capturing the attention of vision researchers in contemporary times. The Vision Transformer (ViT) model effectively models long-range dependencies while utilizing a self-attention mechanism by converting image information into meaningful representations. Moreover, the parallelism property of ViT ensures better scalability and model generalization compared to Recurrent Neural Networks (RNN). However, developing robust ViT models for high-risk vision applications, such as self-driving cars, is critical. Deterministic ViT models are susceptible to noise and adversarial attacks and incapable of yielding a level of confidence in output predictions. Quantifying the confidence (or uncertainty) level in the decision is highly important in such real-world applications. In this work, we introduce a probabilistic framework for ViT to quantify the level of uncertainty in the model's decision. We approximate the posterior distribution of network parameters using variational inference. While progressing through non-linear layers, the first-order Taylor approximation was deployed. The developed framework propagates the mean and covariance of the posterior distribution through layers of the probabilistic ViT model and quantifies uncertainty at the output predictions. Quantifying uncertainty aids in providing warning signals to real-world applications in case of noisy situations. Experimental results from extensive simulation conducted on numerous benchmark datasets (e.g., MNIST and Fashion-MNIST) for image classification tasks exhibit 1) higher accuracy of proposed probabilistic ViT under noise or adversarial attacks compared to the deterministic ViT. 2) Self-evaluation through uncertainty becomes notably pronounced as noise levels escalate. Simulations were conducted at the Texas Advanced Computing Center (TACC) on the Lonestar6 supercomputer node. With the help of this vital resource, we completed all the experiments within a reasonable period. 
    more » « less
  2. Model confidence or uncertainty is critical in autonomous systems as they directly tie to the safety and trustworthiness of the system. The quantification of uncertainty in the output decisions of deep neural networks (DNNs) is a challenging problem. The Bayesian framework enables the estimation of the predictive uncertainty by introducing probability distributions over the (unknown) network weights; however, the propagation of these high-dimensional distributions through multiple layers and non-linear transformations is mathematically intractable. In this work, we propose an extended variational inference (eVI) framework for convolutional neural network (CNN) based on tensor Normal distributions (TNDs) defined over convolutional kernels. Our proposed eVI framework propagates the first two moments (mean and covariance) of these TNDs through all layers of the CNN. We employ first-order Taylor series linearization to approximate the mean and covariances passing through the non-linear activations. The uncertainty in the output decision is given by the propagated covariance of the predictive distribution. Furthermore, we show, through extensive simulations on the MNIST and CIFAR-10 datasets, that the CNN becomes more robust to Gaussian noise and adversarial attacks. 
    more » « less
  3. Implicit neural networks are a general class of learning models that replace the layers in traditional feedforward models with implicit algebraic equations. Compared to traditional learning models, implicit networks offer competitive performance and reduced memory consumption. However, they can remain brittle with respect to input adversarial perturbations. This paper proposes a theoretical and computational framework for robustness verification of implicit neural networks; our framework blends together mixed monotone systems theory and contraction theory. First, given an implicit neural network, we introduce a related embedded network and show that, given an infinity-norm box constraint on the input, the embedded network provides an infinity-norm box overapproximation for the output of the original network. Second, using infinity-matrix measures, we propose sufficient conditions for well-posedness of both the original and embedded system and design an iterative algorithm to compute the infinity-norm box robustness margins for reachability and classification problems. Third, of independent value, we show that employing a suitable relative classifier variable in our analysis will lead to tighter bounds on the certified adversarial robustness in classification problems. Finally, we perform numerical simulations on a Non-Euclidean Monotone Operator Network (NEMON) trained on the MNIST dataset. In these simulations, we compare the accuracy and run time of our mixed monotone contractive approach with the existing robustness verification approaches in the literature for estimating the certified adversarial robustness. 
    more » « less
  4. Markopoulos, Panos P. ; Ouyang, Bing (Ed.)
    We consider the problem of unsupervised (blind) evaluation and assessment of the quality of data used for deep neural network (DNN) RF signal classification. When neural networks train on noisy or mislabeled data, they often (over-)fit to the noise measurements and faulty labels, which leads to significant performance degradation. Also, DNNs are vulnerable to adversarial attacks, which can considerably reduce their classification performance, with extremely small perturbations of their input. In this paper, we consider a new method based on L1-norm principal-component analysis (PCA) to improve the quality of labeled wireless data sets that are used for training a convolutional neural network (CNN), and a deep residual network (ResNet) for RF signal classification. Experiments with data generated for eleven classes of digital and analog modulated signals show that L1-norm tensor conformity curation of the data identifies and removes from the training data set inappropriate class instances that appear due to mislabeling and universal black-box adversarial attacks and drastically improves/restores the classification accuracy of the identified deep neural network architectures. 
    more » « less
  5. Synthetic aperture radar (SAR) image classification is a challenging problem due to the complex imaging mechanism as well as the random speckle noise, which affects radar image interpretation. Recently, convolutional neural networks (CNNs) have been shown to outperform previous state-of-the-art techniques in computer vision tasks owing to their ability to learn relevant features from the data. However, CNNs in particular and neural networks, in general, lack uncertainty quantification and can be easily deceived by adversarial attacks. This paper proposes Bayes-SAR Net, a Bayesian CNN that can perform robust SAR image classification while quantifying the uncertainty or confidence of the network in its decision. Bayes-SAR Net propagates the first two moments (mean and covariance) of the approximate posterior distribution of the network parameters given the data and obtains a predictive mean and covariance of the classification output. Experiments, using the benchmark datasets Flevoland and Oberpfaffenhofen, show superior performance and robustness to Gaussian noise and adversarial attacks, as compared to the SAR-Net homologue. Bayes-SAR Net achieves a test accuracy that is around 10% higher in the case of adversarial perturbation (levels > 0.05). 
    more » « less