Probabilistic Modeling of Deep Features for Out-of-Distribution and Adversarial Detection

09/25/2019
by   Nilesh A. Ahuja, et al.
0

We present a principled approach for detecting out-of-distribution (OOD) and adversarial samples in deep neural networks. Our approach consists in modeling the outputs of the various layers (deep features) with parametric probability distributions once training is completed. At inference, the likelihoods of the deep features w.r.t the previously learnt distributions are calculated and used to derive uncertainty estimates that can discriminate in-distribution samples from OOD samples. We explore the use of two classes of multivariate distributions for modeling the deep features - Gaussian and Gaussian mixture - and study the trade-off between accuracy and computational complexity. We demonstrate benefits of our approach on image features by detecting OOD images and adversarially-generated images, using popular DNN architectures on MNIST and CIFAR10 datasets. We show that more precise modeling of the feature distributions result in significantly improved detection of OOD and adversarial samples; up to 12 percentage points in AUPR and AUROC metrics. We further show that our approach remains extremely effective when applied to video data and associated spatio-temporal features by detecting adversarial samples on activity classification tasks using UCF101 dataset, and the C3D network. To our knowledge, our methodology is the first one reported for reliably detecting white-box adversarial framing, a state-of-the-art adversarial attack for video classifiers.

READ FULL TEXT
research
12/08/2020

Out-Of-Distribution Detection With Subspace Techniques And Probabilistic Modeling Of Features

This paper presents a principled approach for detecting out-of-distribut...
research
12/03/2019

Deep Probabilistic Models to Detect Data Poisoning Attacks

Data poisoning attacks compromise the integrity of machine-learning mode...
research
04/23/2021

Lightweight Detection of Out-of-Distribution and Adversarial Samples via Channel Mean Discrepancy

Detecting out-of-distribution (OOD) and adversarial samples is essential...
research
10/25/2020

Multiscale Score Matching for Out-of-Distribution Detection

We present a new methodology for detecting out-of-distribution (OOD) ima...
research
02/02/2021

pseudo-Bayesian Neural Networks for detecting Out of Distribution Inputs

Conventional Bayesian Neural Networks (BNNs) are known to be capable of ...
research
03/15/2022

Igeood: An Information Geometry Approach to Out-of-Distribution Detection

Reliable out-of-distribution (OOD) detection is fundamental to implement...
research
07/10/2021

Identifying Layers Susceptible to Adversarial Attacks

Common neural network architectures are susceptible to attack by adversa...

Please sign up or login with your details

Forgot password? Click here to reset