N
Nina Narodytska
Researcher at VMware
Publications - 131
Citations - 3226
Nina Narodytska is an academic researcher from VMware. The author has contributed to research in topics: Constraint (information theory) & Voting. The author has an hindex of 27, co-authored 120 publications receiving 2551 citations. Previous affiliations of Nina Narodytska include University of Toronto & University of New South Wales.
Papers
More filters
Proceedings ArticleDOI
Simple Black-Box Adversarial Attacks on Deep Neural Networks
TL;DR: This work focuses on deep convolutional neural networks and demonstrates that adversaries can easily craft adversarial examples even without any internal knowledge of the target network, and proposes schemes that could serve as a litmus test for designing robust networks.
Posted Content
Simple Black-Box Adversarial Perturbations for Deep Networks
TL;DR: This work focuses on deep convolutional neural networks and demonstrates that adversaries can easily craft adversarial examples even without any internal knowledge of the target network.
Proceedings Article
RelGAN: Relational Generative Adversarial Networks for Text Generation.
Journal ArticleDOI
Abduction-Based Explanations for Machine Learning Models
TL;DR: A constraint-agnostic solution for computing explanations for any ML model that exploits abductive reasoning, and imposes the requirement that the ML model can be represented as sets of constraints using some target constraint reasoning system for which the decision problem can be answered with some oracle.
Proceedings Article
Maximum satisfiability using core-guided MAXSAT resolution
Nina Narodytska,Fahiem Bacchus +1 more
TL;DR: Using compressed MAXSAT resolution, this work proposes a new core-guided solver that improves the state-of-the-art, solving significantly more problems than other state of theart solvers on the industrial benchmarks used in the 2013 MAXSat Solver Evaluation.