ECCV18, 20のadversarial examples関連論文リンク集

目視で判断したので、間違っていたり抜けてたりするかもしれませんが、ご容赦ください。

20

Model-Agnostic Boundary-Adversarial Sampling for Test-Time Generalization in Few-Shot learning

Regularization with Latent Space Virtual Adversarial Training

Targeted Attack for Deep Hashing based Retrieval

Multitask Learning Strengthens Adversarial Robustness

Towards Automated Testing and Robustification by Semantic Adversarial Data Generation

Improved Adversarial Training via Learned Optimizer

Reflection Backdoor: A Natural Backdoor Attack on Deep Neural Networks

Indirect Local Attacks for Context-aware Semantic Segmentation Networks

AdvPC: Transferable Adversarial Perturbations on 3D Point Clouds

Adversarial T-shirt! Evading Person Detectors in A Physical World

Bias-based Universal Adversarial Patch Attack for Automatic Check-out

SemanticAdv: Generating Adversarial Examples via Attribute-conditioned Image Editing

Adversarial Ranking Attack and Defense

Attract, Perturb, and Explore: Learning a Feature Alignment Network for Semi-supervised Domain Adaptation

Yet Another Intermediate-Level Attack

Boosting Decision-based Black-box Adversarial Attacks with Random Sign Flip

Spatiotemporal Attacks for Embodied Agents

Open-set Adversarial Defense

Semantic Equivalent Adversarial Data Augmentation for Visual Question Answering

Robust Tracking against Adversarial Attacks

Sparse Adversarial Attack via Perturbation Factorization

Square Attack: a query-efficient black-box adversarial attack via random search

Improving the Transferability of Adversarial Examples with Resized-Diverse-Inputs, Diversity-Ensemble and Region Fitting

Improving Query Efficiency of Black-box Adversarial Attack

What makes fake images detectable? Understanding properties that generalize

Efficient Adversarial Attacks for Visual Object Tracking

PatchAttack: A Black-box Texture-based Attack with Reinforcement Learning

Practical Poisoning Attacks on Neural Networks

Improving Adversarial Robustness by Enforcing Local and Global Compactness

SPARK: Spatial-aware Online Incremental Attack Against Visual Tracking

Patch-wise Attack for Fooling Deep Neural Network

Defense Against Adversarial Attacks via Controlling Gradient Leaking on Embedded Manifolds

Manifold Projection for Adversarial Defense on Face Recognition

Inherent Adversarial Robustness of Deep Spiking Neural Networks: Effects of Discrete Input Encoding and Non-Linear Activations

New Threats against Object Detector with Non-local Block

18

Practical Black-box Attacks on Deep Neural Networks using Efficient Query Mechanisms

Ask, Acquire and Attack: Data-free UAP generation using Class impressions

Improving DNN Robustness to Adversarial Attacks using Jacobian Regularization

Learning Discriminative Video Representations Using Adversarial Perturbations

Transferable Adversarial Perturbations