GEOMETRIC AUGMENTATION FOR ROBUST NEURAL NETWORK CLASSIFIERS
We introduce a novel geometric perspective and unsupervised model augmentation framework for transforming traditional deep (convolutional) neural networks into adversarially robust classifiers. Class-conditional probability densities based on Bayesian nonparametric mixtures of factor analyzers (BNP-MFA) over the input space are used to design soft decision labels for feature to label isometry. Classconditional distributions over features are also learned using BNP-MFA to develop plug-in maximum a posterior (MAP) classifiers to replace the traditional multinomial logistic softmax classification layers. This novel unsupervised augmented framework, which we call geometrically robust networks (GRN), is applied to CIFAR-10, CIFAR-100, and to Radio-ML (a time series dataset for radio modulation recognition). We demonstrate the robustness of GRN models to adversarial attacks from fast gradient sign method, Carlini-Wagner, and projected gradient descent.
Code (0)
등록된 구현이 없습니다.
Tasks
General ClassificationTime SeriesTime Series AnalysisMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Manitest: Are classifiers really invariant?
Invariance to geometric transformations is a highly desirable property of automatic classifiers in many image recognition tasks. Nevertheless, it is unclear to which extent state-of-the-art classifiers are invariant to b…
Data AugmentationEnsemble Augmentation for Deep Neural Networks Using 1-D Time Series Vibration Data
Time-series data are one of the fundamental types of raw data representation used in data-driven techniques. In machine condition monitoring, time-series vibration data are overly used in data mining for deep neural netw…
Data AugmentationGenerative Adversarial NetworkTime SeriesTime Series Analysis+1Geometric Filtering of LLM-Generated Samples for Few-Shot Text Classification
Large language models (LLMs) can generate synthetic training data for text classification, but the quality of generated samples is heterogeneous: some fall in correct class regions of the embedding space while others lan…
Few-Shot Text ClassificationProducing Plankton Classifiers that are Robust to Dataset Shift
Modern plankton high-throughput monitoring relies on deep learning classifiers for species recognition in water ecosystems. Despite satisfactory nominal performances, a significant challenge arises from Dataset Shift, wh…
DiagnosticShadows Don't Lie and Lines Can't Bend! Generative Models don't know Projective Geometry...for now
Generative models can produce impressively realistic images. This paper demonstrates that generated images have geometric features different from those of real images. We build a set of collections of generated images, p…