arXiv is an e-print service in the fields of physics, mathematics, computer science, quantitative biology, quantitative finance and statistics.

WAIC, but Why? Generative Ensembles for Robust Anomaly Detection

arXiv e-Print archive - 2018 via Local arXiv

Keywords: stat.ML, cs.LG

more

arXiv e-Print archive - 2018 via Local arXiv

Keywords: stat.ML, cs.LG

Sanity Checks for Saliency Maps

Neural Information Processing Systems Conference - 2018 via Local Bibsonomy

Keywords: dblp

Neural Information Processing Systems Conference - 2018 via Local Bibsonomy

Keywords: dblp

Second-Order Adversarial Attack and Certifiable Robustness

arXiv e-Print archive - 2018 via Local Bibsonomy

Keywords: dblp

arXiv e-Print archive - 2018 via Local Bibsonomy

Keywords: dblp

Certified Robustness to Adversarial Examples with Differential Privacy

arXiv e-Print archive - 2018 via Local arXiv

Keywords: stat.ML, cs.AI, cs.CR, cs.LG

more

arXiv e-Print archive - 2018 via Local arXiv

Keywords: stat.ML, cs.AI, cs.CR, cs.LG

On the Effectiveness of Interval Bound Propagation for Training Verifiably Robust Models

arXiv e-Print archive - 2018 via Local arXiv

Keywords: cs.LG, cs.CR, stat.ML

more

arXiv e-Print archive - 2018 via Local arXiv

Keywords: cs.LG, cs.CR, stat.ML

Deep-RBF Networks Revisited: Robust Classification with Rejection

arXiv e-Print archive - 2018 via Local Bibsonomy

Keywords: dblp

arXiv e-Print archive - 2018 via Local Bibsonomy

Keywords: dblp

Neural Networks with Structural Resistance to Adversarial Attacks

arXiv e-Print archive - 2018 via Local arXiv

Keywords: stat.ML, cs.CR, cs.LG, cs.NE

more

arXiv e-Print archive - 2018 via Local arXiv

Keywords: stat.ML, cs.CR, cs.LG, cs.NE

On the importance of single directions for generalization

arXiv e-Print archive - 2018 via Local arXiv

Keywords: stat.ML, cs.AI, cs.LG, cs.NE

more

arXiv e-Print archive - 2018 via Local arXiv

Keywords: stat.ML, cs.AI, cs.LG, cs.NE

Improving Transferability of Adversarial Examples with Input Diversity

arXiv e-Print archive - 2018 via Local arXiv

Keywords: cs.CV, cs.LG, stat.ML

more

arXiv e-Print archive - 2018 via Local arXiv

Keywords: cs.CV, cs.LG, stat.ML

Beyond Pixel Norm-Balls: Parametric Adversaries using an Analytically Differentiable Renderer

arXiv e-Print archive - 2018 via Local arXiv

Keywords: cs.LG, cs.CV, cs.GR, stat.ML

more

arXiv e-Print archive - 2018 via Local arXiv

Keywords: cs.LG, cs.CV, cs.GR, stat.ML

Breaking Transferability of Adversarial Samples with Randomness

arXiv e-Print archive - 2018 via Local Bibsonomy

Keywords: dblp

arXiv e-Print archive - 2018 via Local Bibsonomy

Keywords: dblp

Cost-Sensitive Robustness against Adversarial Examples

arXiv e-Print archive - 2018 via Local Bibsonomy

Keywords: dblp

arXiv e-Print archive - 2018 via Local Bibsonomy

Keywords: dblp

Black-box Adversarial Attacks with Limited Queries and Information

arXiv e-Print archive - 2018 via Local arXiv

Keywords: cs.CV, cs.CR, stat.ML

more

arXiv e-Print archive - 2018 via Local arXiv

Keywords: cs.CV, cs.CR, stat.ML

On the Intriguing Connections of Regularization, Input Gradients and Transferability of Evasion and Poisoning Attacks

arXiv e-Print archive - 2018 via Local arXiv

Keywords: cs.LG, cs.CR, stat.ML, 68T10, 68T45

more

arXiv e-Print archive - 2018 via Local arXiv

Keywords: cs.LG, cs.CR, stat.ML, 68T10, 68T45

On the Geometry of Adversarial Examples

arXiv e-Print archive - 2018 via Local Bibsonomy

Keywords: dblp

arXiv e-Print archive - 2018 via Local Bibsonomy

Keywords: dblp

The Limitations of Model Uncertainty in Adversarial Settings

arXiv e-Print archive - 2018 via Local Bibsonomy

Keywords: dblp

arXiv e-Print archive - 2018 via Local Bibsonomy

Keywords: dblp

The Secret Sharer: Measuring Unintended Neural Network Memorization & Extracting Secrets

arXiv e-Print archive - 2018 via Local Bibsonomy

Keywords: dblp

arXiv e-Print archive - 2018 via Local Bibsonomy

Keywords: dblp

Playing the Game of Universal Adversarial Perturbations

arXiv e-Print archive - 2018 via Local arXiv

Keywords: cs.LG, cs.CV, stat.ML

more

arXiv e-Print archive - 2018 via Local arXiv

Keywords: cs.LG, cs.CV, stat.ML

Are adversarial examples inevitable?

arXiv e-Print archive - 2018 via Local Bibsonomy

Keywords: dblp

arXiv e-Print archive - 2018 via Local Bibsonomy

Keywords: dblp

Fortified Networks: Improving the Robustness of Deep Networks by Modeling the Manifold of Hidden Representations

arXiv e-Print archive - 2018 via Local Bibsonomy

Keywords: dblp

arXiv e-Print archive - 2018 via Local Bibsonomy

Keywords: dblp

Towards the first adversarially robust neural network model on MNIST

arXiv e-Print archive - 2018 via Local arXiv

Keywords: cs.CV

more

arXiv e-Print archive - 2018 via Local arXiv

Keywords: cs.CV

Adversarial Training Versus Weight Decay

arXiv e-Print archive - 2018 via Local arXiv

Keywords: cs.LG, stat.ML

more

arXiv e-Print archive - 2018 via Local arXiv

Keywords: cs.LG, stat.ML

Model-Based Reinforcement Learning via Meta-Policy Optimization

Conference on Robot Learning - 2018 via Local Bibsonomy

Keywords: dblp

Conference on Robot Learning - 2018 via Local Bibsonomy

Keywords: dblp

Explaining Image Classifiers by Counterfactual Generation

arXiv e-Print archive - 2018 via Local arXiv

Keywords: cs.CV

more

arXiv e-Print archive - 2018 via Local arXiv

Keywords: cs.CV

Temporal Difference Variational Auto-Encoder

arXiv e-Print archive - 2018 via Local Bibsonomy

Keywords: dblp

arXiv e-Print archive - 2018 via Local Bibsonomy

Keywords: dblp

Meta-Learning Update Rules for Unsupervised Representation Learning

arXiv e-Print archive - 2018 via Local arXiv

Keywords: cs.LG, cs.NE, stat.ML

more

arXiv e-Print archive - 2018 via Local arXiv

Keywords: cs.LG, cs.NE, stat.ML

Learning to Navigate in Cities Without a Map

arXiv e-Print archive - 2018 via Local Bibsonomy

Keywords: dblp

arXiv e-Print archive - 2018 via Local Bibsonomy

Keywords: dblp

Systematic Generalization: What Is Required and Can It Be Learned?

arXiv e-Print archive - 2018 via Local arXiv

Keywords: cs.CL, cs.AI

more

arXiv e-Print archive - 2018 via Local arXiv

Keywords: cs.CL, cs.AI

Diversity is All You Need: Learning Skills without a Reward Function

arXiv e-Print archive - 2018 via Local Bibsonomy

Keywords: dblp

arXiv e-Print archive - 2018 via Local Bibsonomy

Keywords: dblp

Effective Ways to Build and Evaluate Individual Survival Distributions

arXiv e-Print archive - 2018 via Local arXiv

Keywords: cs.LG, stat.ML

more

arXiv e-Print archive - 2018 via Local arXiv

Keywords: cs.LG, stat.ML

Deep k-Nearest Neighbors: Towards Confident, Interpretable and Robust Deep Learning

arXiv e-Print archive - 2018 via Local arXiv

Keywords: cs.LG, stat.ML

more

arXiv e-Print archive - 2018 via Local arXiv

Keywords: cs.LG, stat.ML

Towards Imperceptible and Robust Adversarial Example Attacks against Neural Networks

arXiv e-Print archive - 2018 via Local arXiv

Keywords: cs.LG, cs.CR, stat.ML

more

arXiv e-Print archive - 2018 via Local arXiv

Keywords: cs.LG, cs.CR, stat.ML

Spatially Transformed Adversarial Examples

arXiv e-Print archive - 2018 via Local Bibsonomy

Keywords: dblp

arXiv e-Print archive - 2018 via Local Bibsonomy

Keywords: dblp

Robustness of Rotation-Equivariant Networks to Adversarial Perturbations

arXiv e-Print archive - 2018 via Local Bibsonomy

Keywords: dblp

arXiv e-Print archive - 2018 via Local Bibsonomy

Keywords: dblp

Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples

arXiv e-Print archive - 2018 via Local Bibsonomy

Keywords: dblp

arXiv e-Print archive - 2018 via Local Bibsonomy

Keywords: dblp

ADef: an Iterative Algorithm to Construct Adversarial Deformations

arXiv e-Print archive - 2018 via Local Bibsonomy

Keywords: dblp

arXiv e-Print archive - 2018 via Local Bibsonomy

Keywords: dblp

On the Robustness of the CVPR 2018 White-Box Adversarial Example Defenses

arXiv e-Print archive - 2018 via Local Bibsonomy

Keywords: dblp

arXiv e-Print archive - 2018 via Local Bibsonomy

Keywords: dblp

There Is No Free Lunch In Adversarial Robustness (But There Are Unexpected Benefits)

arXiv e-Print archive - 2018 via Local Bibsonomy

Keywords: dblp

arXiv e-Print archive - 2018 via Local Bibsonomy

Keywords: dblp

Protecting JPEG Images Against Adversarial Attacks

arXiv e-Print archive - 2018 via Local Bibsonomy

Keywords: dblp

arXiv e-Print archive - 2018 via Local Bibsonomy

Keywords: dblp

Out-distribution training confers robustness to deep neural networks

arXiv e-Print archive - 2018 via Local Bibsonomy

Keywords: dblp

arXiv e-Print archive - 2018 via Local Bibsonomy

Keywords: dblp

Adversarial Defense based on Structure-to-Signal Autoencoders

arXiv e-Print archive - 2018 via Local Bibsonomy

Keywords: dblp

arXiv e-Print archive - 2018 via Local Bibsonomy

Keywords: dblp

Improving MMD-GAN Training with Repulsive Loss Function

arXiv e-Print archive - 2018 via Local arXiv

Keywords: cs.LG, cs.CV, stat.ML

more

arXiv e-Print archive - 2018 via Local arXiv

Keywords: cs.LG, cs.CV, stat.ML

Learning a SAT Solver from Single-Bit Supervision

arXiv e-Print archive - 2018 via Local Bibsonomy

Keywords: dblp

arXiv e-Print archive - 2018 via Local Bibsonomy

Keywords: dblp

Data Augmentation for Skin Lesion Analysis

arXiv e-Print archive - 2018 via Local arXiv

Keywords: cs.CV

more

arXiv e-Print archive - 2018 via Local arXiv

Keywords: cs.CV

Investigating Human Priors for Playing Video Games

arXiv e-Print archive - 2018 via Local arXiv

Keywords: cs.AI, cs.LG

more

arXiv e-Print archive - 2018 via Local arXiv

Keywords: cs.AI, cs.LG

Neural Ordinary Differential Equations

arXiv e-Print archive - 2018 via Local arXiv

Keywords: cs.LG, cs.AI, stat.ML

more

arXiv e-Print archive - 2018 via Local arXiv

Keywords: cs.LG, cs.AI, stat.ML

Do Deep Generative Models Know What They Don't Know?

arXiv e-Print archive - 2018 via Local arXiv

Keywords: stat.ML, cs.LG

more

arXiv e-Print archive - 2018 via Local arXiv

Keywords: stat.ML, cs.LG

Learning Confidence for Out-of-Distribution Detection in Neural Networks

arXiv e-Print archive - 2018 via Local arXiv

Keywords: stat.ML, cs.LG

more

arXiv e-Print archive - 2018 via Local arXiv

Keywords: stat.ML, cs.LG

Discovery of Latent 3D Keypoints via End-to-end Geometric Reasoning

arXiv e-Print archive - 2018 via Local arXiv

Keywords: cs.CV, cs.LG, stat.ML

more

arXiv e-Print archive - 2018 via Local arXiv

Keywords: cs.CV, cs.LG, stat.ML

Learning Latent Dynamics for Planning from Pixels

arXiv e-Print archive - 2018 via Local arXiv

Keywords: cs.LG, cs.AI, stat.ML

more

arXiv e-Print archive - 2018 via Local arXiv

Keywords: cs.LG, cs.AI, stat.ML

Gradient Reversal Against Discrimination

arXiv e-Print archive - 2018 via Local arXiv

Keywords: stat.ML, cs.AI, cs.LG

more

arXiv e-Print archive - 2018 via Local arXiv

Keywords: stat.ML, cs.AI, cs.LG

BSN: Boundary Sensitive Network for Temporal Action Proposal Generation

arXiv e-Print archive - 2018 via Local arXiv

Keywords: cs.CV

more

arXiv e-Print archive - 2018 via Local arXiv

Keywords: cs.CV

Relational Forward Models for Multi-Agent Learning

arXiv e-Print archive - 2018 via Local arXiv

Keywords: cs.LG, cs.AI, cs.MA, stat.ML

more

arXiv e-Print archive - 2018 via Local arXiv

Keywords: cs.LG, cs.AI, cs.MA, stat.ML

Woulda, Coulda, Shoulda: Counterfactually-Guided Policy Search

arXiv e-Print archive - 2018 via Local arXiv

Keywords: cs.LG, stat.ML

more

arXiv e-Print archive - 2018 via Local arXiv

Keywords: cs.LG, stat.ML

Learning to Learn without Forgetting By Maximizing Transfer and Minimizing Interference

arXiv e-Print archive - 2018 via Local arXiv

Keywords: cs.LG, cs.AI, stat.ML

more

arXiv e-Print archive - 2018 via Local arXiv

Keywords: cs.LG, cs.AI, stat.ML

An Intriguing Failing of Convolutional Neural Networks and the CoordConv Solution

arXiv e-Print archive - 2018 via Local arXiv

Keywords: cs.CV, cs.LG, stat.ML

more

arXiv e-Print archive - 2018 via Local arXiv

Keywords: cs.CV, cs.LG, stat.ML

Adversarial Reprogramming of Neural Networks

arXiv e-Print archive - 2018 via Local arXiv

Keywords: cs.LG, cs.CR, cs.CV, stat.ML

more

arXiv e-Print archive - 2018 via Local arXiv

Keywords: cs.LG, cs.CR, cs.CV, stat.ML

Learning Plannable Representations with Causal InfoGAN

arXiv e-Print archive - 2018 via Local arXiv

Keywords: cs.LG, cs.AI, cs.CV, cs.NE, cs.RO, stat.ML

more

arXiv e-Print archive - 2018 via Local arXiv

Keywords: cs.LG, cs.AI, cs.CV, cs.NE, cs.RO, stat.ML

Intrinsic Social Motivation via Causal Influence in Multi-Agent RL

arXiv e-Print archive - 2018 via Local arXiv

Keywords: cs.LG, cs.AI, cs.MA, stat.ML

more

arXiv e-Print archive - 2018 via Local arXiv

Keywords: cs.LG, cs.AI, cs.MA, stat.ML

Natural Environment Benchmarks for Reinforcement Learning

arXiv e-Print archive - 2018 via Local arXiv

Keywords: cs.LG, cs.AI, stat.ML

more

arXiv e-Print archive - 2018 via Local arXiv

Keywords: cs.LG, cs.AI, stat.ML

Reward learning from human preferences and demonstrations in Atari

arXiv e-Print archive - 2018 via Local arXiv

Keywords: cs.LG, cs.AI, cs.NE, stat.ML

more

arXiv e-Print archive - 2018 via Local arXiv

Keywords: cs.LG, cs.AI, cs.NE, stat.ML

Model-Based Active Exploration

arXiv e-Print archive - 2018 via Local arXiv

Keywords: cs.LG, cs.AI, cs.IT, cs.NE, math.IT, stat.ML

more

arXiv e-Print archive - 2018 via Local arXiv

Keywords: cs.LG, cs.AI, cs.IT, cs.NE, math.IT, stat.ML

Episodic Curiosity through Reachability

arXiv e-Print archive - 2018 via Local arXiv

Keywords: cs.LG, cs.AI, cs.CV, cs.RO, stat.ML

more

arXiv e-Print archive - 2018 via Local arXiv

Keywords: cs.LG, cs.AI, cs.CV, cs.RO, stat.ML

Large-Scale Study of Curiosity-Driven Learning

arXiv e-Print archive - 2018 via Local arXiv

Keywords: cs.LG, cs.AI, cs.CV, cs.RO, stat.ML

more

arXiv e-Print archive - 2018 via Local arXiv

Keywords: cs.LG, cs.AI, cs.CV, cs.RO, stat.ML

Multi-task Deep Reinforcement Learning with PopArt

arXiv e-Print archive - 2018 via Local arXiv

Keywords: cs.LG, stat.ML

more

arXiv e-Print archive - 2018 via Local arXiv

Keywords: cs.LG, stat.ML

IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures

arXiv e-Print archive - 2018 via Local arXiv

Keywords: cs.LG, cs.AI

more

arXiv e-Print archive - 2018 via Local arXiv

Keywords: cs.LG, cs.AI

Language GANs Falling Short

arXiv e-Print archive - 2018 via Local arXiv

Keywords: cs.CL, cs.LG

more

arXiv e-Print archive - 2018 via Local arXiv

Keywords: cs.CL, cs.LG