TORAX: A Fast and Differentiable Tokamak Transport Simulator in JAX
TORAX：JAX 中一个快速且可微的托卡马克输运模拟器
AI总结 介绍基于 JAX 框架的开源可微托卡马克输运模拟器 TORAX，它求解多种输运耦合方程，融合物理与机器学习模型，利用 JAX 特性实现快速运行及微分，经与 RAPTOR 代码验证，为托卡马克相关研究提供有力工具。
Comments 16 pages, 7 figures
作者
Ian Goodfellow
Generative Models
MONA: Myopic Optimization with Non-myopic Approval Can Mitigate Multi-step Reward Hacking
Adversarial Training Methods for Semi-Supervised Text Classification
Comments Published as a conference paper at ICLR 2017
Sanity Checks for Saliency Maps
Comments Updating Guided Backprop experiments due to bug. The results and conclusions remain the same
Enabling certification of verification-agnostic networks via memory-efficient semidefinite programming
A domain agnostic measure for monitoring and evaluating GANs
Ensemble Adversarial Training: Attacks and Defenses
Comments 22 pages, 5 figures, International Conference on Learning Representations (ICLR) 2018 (amended in April 2020 to include subsequent attacks that significantly reduced the robustness of our models)
Creating High Resolution Images with a Latent Adversarial Generator
MixMatch: A Holistic Approach to Semi-Supervised Learning
Adversarial Reprogramming of Neural Networks
Journal ref International Conference on Learning Representations 2019
Adversarial Examples that Fool both Computer Vision and Time-Limited Humans
Journal ref Advances in Neural Information Processing Systems, 2018
Self-Attention Generative Adversarial Networks
Realistic Evaluation of Deep Semi-Supervised Learning Algorithms
Journal ref NeurIPS 2018 Proceedings
Imperceptible, Robust, and Targeted Adversarial Examples for Automatic Speech Recognition
Comments International Conference on Machine Learning (ICML), 2019
A Research Agenda: Dynamic Models to Defend Against Correlated Attacks
Discriminator Rejection Sampling
Comments Published as a conference paper at ICLR 2019
On Evaluating Adversarial Robustness
Comments Living document; source available at https://github.com/evaluating-adversarial-robustness/adv-eval-paper/
Deep Learning with Differential Privacy
Journal ref Proceedings of the 2016 ACM SIGSAC Conference on Computer and Communications Security (ACM CCS), pp. 308-318, 2016
On the Protection of Private Information in Machine Learning Systems: Two Recent Approaches
Journal ref IEEE 30th Computer Security Foundations Symposium (CSF), pages 1--6, 2017
New CleverHans Feature: Better Adversarial Robustness Evaluations with Attack Bundling
Local Explanation Methods for Deep Neural Networks Lack Sensitivity to Parameter Values
Comments Workshop Track International Conference on Learning Representations (ICLR)
Unrestricted Adversarial Examples
Adversarial Spheres
Skill Rating for Generative Models
TensorFuzz: Debugging Neural Networks with Coverage-Guided Fuzzing
Comments Preprint - work in progress
Understanding and Improving Interpolation in Autoencoders via an Adversarial Regularizer
Motivating the Rules of the Game for Adversarial Example Research
Technical Report on the CleverHans v2.1.0 Adversarial Examples Library
Comments Technical report for https://github.com/tensorflow/cleverhans
