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

Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networks

arXiv e-Print archive - 2017 via Local arXiv

Keywords: cs.LG, stat.ML

more

arXiv e-Print archive - 2017 via Local arXiv

Keywords: cs.LG, stat.ML

UPSET and ANGRI : Breaking High Performance Image Classifiers

arXiv e-Print archive - 2017 via Local Bibsonomy

Keywords: dblp

arXiv e-Print archive - 2017 via Local Bibsonomy

Keywords: dblp

Improving Network Robustness against Adversarial Attacks with Compact Convolution

arXiv e-Print archive - 2017 via Local Bibsonomy

Keywords: dblp

arXiv e-Print archive - 2017 via Local Bibsonomy

Keywords: dblp

Regularizing Neural Networks by Penalizing Confident Output Distributions

arXiv e-Print archive - 2017 via Local arXiv

Keywords: cs.NE, cs.LG

more

arXiv e-Print archive - 2017 via Local arXiv

Keywords: cs.NE, cs.LG

Enhanced Attacks on Defensively Distilled Deep Neural Networks

arXiv e-Print archive - 2017 via Local Bibsonomy

Keywords: dblp

arXiv e-Print archive - 2017 via Local Bibsonomy

Keywords: dblp

Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)

arXiv e-Print archive - 2017 via Local arXiv

Keywords: stat.ML

more

arXiv e-Print archive - 2017 via Local arXiv

Keywords: stat.ML

On the Robustness of Convolutional Neural Networks to Internal Architecture and Weight Perturbations

arXiv e-Print archive - 2017 via Local Bibsonomy

Keywords: dblp

arXiv e-Print archive - 2017 via Local Bibsonomy

Keywords: dblp

AE-GAN: adversarial eliminating with GAN

arXiv e-Print archive - 2017 via Local Bibsonomy

Keywords: dblp

arXiv e-Print archive - 2017 via Local Bibsonomy

Keywords: dblp

Towards A Rigorous Science of Interpretable Machine Learning

arXiv e-Print archive - 2017 via Local arXiv

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

more

arXiv e-Print archive - 2017 via Local arXiv

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

Learning Robust Rewards with Adversarial Inverse Reinforcement Learning

arXiv e-Print archive - 2017 via Local Bibsonomy

Keywords: dblp

arXiv e-Print archive - 2017 via Local Bibsonomy

Keywords: dblp

The Promise and Peril of Human Evaluation for Model Interpretability

arXiv e-Print archive - 2017 via Local arXiv

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

more

arXiv e-Print archive - 2017 via Local arXiv

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

Interpretable & Explorable Approximations of Black Box Models

arXiv e-Print archive - 2017 via Local Bibsonomy

Keywords: dblp

arXiv e-Print archive - 2017 via Local Bibsonomy

Keywords: dblp

Decoupled Weight Decay Regularization

arXiv e-Print archive - 2017 via Local arXiv

Keywords: cs.LG, cs.NE, math.OC

more

arXiv e-Print archive - 2017 via Local arXiv

Keywords: cs.LG, cs.NE, math.OC

The Marginal Value of Adaptive Gradient Methods in Machine Learning

arXiv e-Print archive - 2017 via Local Bibsonomy

Keywords: dblp

arXiv e-Print archive - 2017 via Local Bibsonomy

Keywords: dblp

Analyzing the Robustness of Nearest Neighbors to Adversarial Examples

arXiv e-Print archive - 2017 via Local Bibsonomy

Keywords: dblp

arXiv e-Print archive - 2017 via Local Bibsonomy

Keywords: dblp

On Calibration of Modern Neural Networks

arXiv e-Print archive - 2017 via Local arXiv

Keywords: cs.LG

more

arXiv e-Print archive - 2017 via Local arXiv

Keywords: cs.LG

Interpretation of Neural Networks is Fragile

arXiv e-Print archive - 2017 via Local Bibsonomy

Keywords: dblp

arXiv e-Print archive - 2017 via Local Bibsonomy

Keywords: dblp

Attacking the Madry Defense Model with $L_1$-based Adversarial Examples

arXiv e-Print archive - 2017 via Local arXiv

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

more

arXiv e-Print archive - 2017 via Local arXiv

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

Geometric robustness of deep networks: analysis and improvement

arXiv e-Print archive - 2017 via Local Bibsonomy

Keywords: dblp

arXiv e-Print archive - 2017 via Local Bibsonomy

Keywords: dblp

Provable defenses against adversarial examples via the convex outer adversarial polytope

arXiv e-Print archive - 2017 via Local Bibsonomy

Keywords: dblp

arXiv e-Print archive - 2017 via Local Bibsonomy

Keywords: dblp

Progressive Growing of GANs for Improved Quality, Stability, and Variation

arXiv e-Print archive - 2017 via Local Bibsonomy

Keywords: dblp

arXiv e-Print archive - 2017 via Local Bibsonomy

Keywords: dblp

TURN TAP: Temporal Unit Regression Network for Temporal Action Proposals

arXiv e-Print archive - 2017 via Local arXiv

Keywords: cs.CV

more

arXiv e-Print archive - 2017 via Local arXiv

Keywords: cs.CV

Temporal Action Detection with Structured Segment Networks

arXiv e-Print archive - 2017 via Local arXiv

Keywords: cs.CV

more

arXiv e-Print archive - 2017 via Local arXiv

Keywords: cs.CV

One pixel attack for fooling deep neural networks

arXiv e-Print archive - 2017 via Local arXiv

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

more

arXiv e-Print archive - 2017 via Local arXiv

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

AttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adversarial Networks

arXiv e-Print archive - 2017 via Local arXiv

Keywords: cs.CV

more

arXiv e-Print archive - 2017 via Local arXiv

Keywords: cs.CV

Visualizing the Loss Landscape of Neural Nets

arXiv e-Print archive - 2017 via Local arXiv

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

more

arXiv e-Print archive - 2017 via Local arXiv

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

Emergence of Grounded Compositional Language in Multi-Agent Populations

arXiv e-Print archive - 2017 via Local arXiv

Keywords: cs.AI, cs.CL

more

arXiv e-Print archive - 2017 via Local arXiv

Keywords: cs.AI, cs.CL

$S^4$Net: Single Stage Salient-Instance Segmentation

arXiv e-Print archive - 2017 via Local arXiv

Keywords: cs.CV

more

arXiv e-Print archive - 2017 via Local arXiv

Keywords: cs.CV

The Do's and Don'ts for CNN-based Face Verification

arXiv e-Print archive - 2017 via Local arXiv

Keywords: cs.CV

more

arXiv e-Print archive - 2017 via Local arXiv

Keywords: cs.CV

Deep Extreme Cut: From Extreme Points to Object Segmentation

arXiv e-Print archive - 2017 via Local arXiv

Keywords: cs.CV

more

arXiv e-Print archive - 2017 via Local arXiv

Keywords: cs.CV

Learning with Opponent-Learning Awareness

arXiv e-Print archive - 2017 via Local arXiv

Keywords: cs.AI, cs.GT

more

arXiv e-Print archive - 2017 via Local arXiv

Keywords: cs.AI, cs.GT

Learning by Asking Questions

arXiv e-Print archive - 2017 via Local arXiv

Keywords: cs.CV, cs.CL, cs.LG

more

arXiv e-Print archive - 2017 via Local arXiv

Keywords: cs.CV, cs.CL, cs.LG

Embodied Question Answering

arXiv e-Print archive - 2017 via Local arXiv

Keywords: cs.CV, cs.AI, cs.CL, cs.LG

more

arXiv e-Print archive - 2017 via Local arXiv

Keywords: cs.CV, cs.AI, cs.CL, cs.LG

Adversarial Attacks on Neural Network Policies

arXiv e-Print archive - 2017 via Local arXiv

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

more

arXiv e-Print archive - 2017 via Local arXiv

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

Wild Patterns: Ten Years After the Rise of Adversarial Machine Learning

arXiv e-Print archive - 2017 via Local arXiv

Keywords: cs.CV, cs.CR, cs.GT, cs.LG

more

arXiv e-Print archive - 2017 via Local arXiv

Keywords: cs.CV, cs.CR, cs.GT, cs.LG

Adversarial Examples: Attacks and Defenses for Deep Learning

arXiv e-Print archive - 2017 via Local arXiv

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

more

arXiv e-Print archive - 2017 via Local arXiv

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

Detecting Adversarial Samples from Artifacts

arXiv e-Print archive - 2017 via Local arXiv

Keywords: stat.ML, cs.LG

more

arXiv e-Print archive - 2017 via Local arXiv

Keywords: stat.ML, cs.LG

Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methods

arXiv e-Print archive - 2017 via Local arXiv

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

more

arXiv e-Print archive - 2017 via Local arXiv

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

On the (Statistical) Detection of Adversarial Examples

arXiv e-Print archive - 2017 via Local arXiv

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

more

arXiv e-Print archive - 2017 via Local arXiv

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

Improving the Adversarial Robustness and Interpretability of Deep Neural Networks by Regularizing their Input Gradients

arXiv e-Print archive - 2017 via Local arXiv

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

more

arXiv e-Print archive - 2017 via Local arXiv

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

Biologically inspired protection of deep networks from adversarial attacks

arXiv e-Print archive - 2017 via Local arXiv

Keywords: stat.ML, cs.LG, q-bio.NC

more

arXiv e-Print archive - 2017 via Local arXiv

Keywords: stat.ML, cs.LG, q-bio.NC

Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networks

arXiv e-Print archive - 2017 via Local arXiv

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

more

arXiv e-Print archive - 2017 via Local arXiv

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

Certifying Some Distributional Robustness with Principled Adversarial Training

arXiv e-Print archive - 2017 via Local arXiv

Keywords: stat.ML, cs.LG

more

arXiv e-Print archive - 2017 via Local arXiv

Keywords: stat.ML, cs.LG

Efficient Defenses Against Adversarial Attacks

arXiv e-Print archive - 2017 via Local arXiv

Keywords: cs.LG

more

arXiv e-Print archive - 2017 via Local arXiv

Keywords: cs.LG

Towards Robust Neural Networks via Random Self-ensemble

arXiv e-Print archive - 2017 via Local arXiv

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

more

arXiv e-Print archive - 2017 via Local arXiv

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

Towards Reverse-Engineering Black-Box Neural Networks

arXiv e-Print archive - 2017 via Local arXiv

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

more

arXiv e-Print archive - 2017 via Local arXiv

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

Comment on "Biologically inspired protection of deep networks from adversarial attacks"

arXiv e-Print archive - 2017 via Local arXiv

Keywords: stat.ML, cs.LG, q-bio.NC

more

arXiv e-Print archive - 2017 via Local arXiv

Keywords: stat.ML, cs.LG, q-bio.NC

ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Models

arXiv e-Print archive - 2017 via Local arXiv

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

more

arXiv e-Print archive - 2017 via Local arXiv

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

Adversarial Robustness: Softmax versus Openmax

arXiv e-Print archive - 2017 via Local arXiv

Keywords: cs.CV

more

arXiv e-Print archive - 2017 via Local arXiv

Keywords: cs.CV

A Rotation and a Translation Suffice: Fooling CNNs with Simple Transformations

arXiv e-Print archive - 2017 via Local arXiv

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

more

arXiv e-Print archive - 2017 via Local arXiv

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

NO Need to Worry about Adversarial Examples in Object Detection in Autonomous Vehicles

arXiv e-Print archive - 2017 via Local arXiv

Keywords: cs.CV, cs.AI, cs.CR

more

arXiv e-Print archive - 2017 via Local arXiv

Keywords: cs.CV, cs.AI, cs.CR

Towards Deep Learning Models Resistant to Adversarial Attacks

arXiv e-Print archive - 2017 via Local arXiv

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

more

arXiv e-Print archive - 2017 via Local arXiv

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

Ensemble Adversarial Training: Attacks and Defenses

arXiv e-Print archive - 2017 via Local arXiv

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

more

arXiv e-Print archive - 2017 via Local arXiv

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

Prototypical Networks for Few-shot Learning

arXiv e-Print archive - 2017 via Local arXiv

Keywords: cs.LG, stat.ML

more

arXiv e-Print archive - 2017 via Local arXiv

Keywords: cs.LG, stat.ML

Word Translation Without Parallel Data

arXiv e-Print archive - 2017 via Local arXiv

Keywords: cs.CL

more

arXiv e-Print archive - 2017 via Local arXiv

Keywords: cs.CL

Continuous Adaptation via Meta-Learning in Nonstationary and Competitive Environments

arXiv e-Print archive - 2017 via Local arXiv

Keywords: cs.LG, cs.AI

more

arXiv e-Print archive - 2017 via Local arXiv

Keywords: cs.LG, cs.AI

Learned in Translation: Contextualized Word Vectors

arXiv e-Print archive - 2017 via Local arXiv

Keywords: cs.CL, cs.AI, cs.LG

more

arXiv e-Print archive - 2017 via Local arXiv

Keywords: cs.CL, cs.AI, cs.LG

Neural Discrete Representation Learning

arXiv e-Print archive - 2017 via Local arXiv

Keywords: cs.LG

more

arXiv e-Print archive - 2017 via Local arXiv

Keywords: cs.LG

Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks

arXiv e-Print archive - 2017 via Local arXiv

Keywords: cs.CV

more

arXiv e-Print archive - 2017 via Local arXiv

Keywords: cs.CV

The Trimmed Lasso: Sparsity and Robustness

arXiv e-Print archive - 2017 via Local arXiv

Keywords: stat.ME, math.OC, math.ST, stat.CO, stat.ML, stat.TH

more

arXiv e-Print archive - 2017 via Local arXiv

Keywords: stat.ME, math.OC, math.ST, stat.CO, stat.ML, stat.TH

Focal Loss for Dense Object Detection

arXiv e-Print archive - 2017 via Local arXiv

Keywords: cs.CV

more

arXiv e-Print archive - 2017 via Local arXiv

Keywords: cs.CV