ICCV17, 19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。

19

Adversarial Robustness vs. Model Compression, or Both?

On the Design of Black-Box Adversarial Examples by Leveraging Gradient-Free Optimization and Operator Splitting Method

What Else Can Fool Deep Learning? Addressing Color Constancy Errors on Deep Neural Network Performance

Evaluating Robustness of Deep Image Super-Resolution Against Adversarial Attacks

Towards Adversarially Robust Object Detection

Generative Adversarial Minority Oversampling

DUP-Net: Denoiser and Upsampler Network for 3D Adversarial Point Clouds Defense

Fooling Network Interpretation in Image Classification

SpatialSense: An Adversarially Crowdsourced Benchmark for Spatial Relation Recognition

Adversarial Defense via Learning to Generate Diverse Attacks

Universal Adversarial Perturbation via Prior Driven Uncertainty Approximation

Understanding Deep Networks via Extremal Perturbations and Smooth Masks

Adversarial Feedback Loop

Adversarial Defense by Restricting the Hidden Space of Deep Neural Networks

Adversarial Fine-Grained Composition Learning for Unseen Attribute-Object Recognition

AdvIT: Adversarial Frames Identifier Based on Temporal Consistency in Videos

Why Does a Visual Question Have Different Answers?

Sparse and Imperceivable Adversarial Attacks

Enhancing Adversarial Example Transferability With an Intermediate Level Attack

Semantic Adversarial Attacks: Parametric Transformations That Fool Deep Classifiers

Hilbert-Based Generative Defense for Adversarial Examples

Physical Adversarial Textures That Fool Visual Object Tracking

The LogBarrier Adversarial Attack: Making Effective Use of Decision Boundary Information

Improving Adversarial Robustness via Guided Complement Entropy

Universal Perturbation Attack Against Image Retrieval

Defending Against Universal Perturbations With Shared Adversarial Training

Guessing Smart: Biased Sampling for Efficient Black-Box Adversarial Attacks

Targeted Mismatch Adversarial Attack: Query With a Flower to Retrieve the Tower

Bilateral Adversarial Training: Towards Fast Training of More Robust Models Against Adversarial Attacks

CIIDefence: Defeating Adversarial Attacks by Fusing Class-Specific Image Inpainting and Image Denoising

FDA: Feature Disruptive Attack

advPattern: Physical-World Attacks on Deep Person Re-Identification via Adversarially Transformable Patterns

17

SafetyNet: Detecting and Rejecting Adversarial Examples Robustly

Adversarial Examples for Semantic Segmentation and Object Detection

Adversarial Image Perturbation for Privacy Protection -- A Game Theory Perspective

Interpretable Explanations of Black Boxes by Meaningful Perturbation

Universal Adversarial Perturbations Against Semantic Image Segmentation

Guided Perturbations: Self-Corrective Behavior in Convolutional Neural Networks

Adversarial Examples Detection in Deep Networks With Convolutional Filter Statistics