Browse > Adversarial > Adversarial Defense

Adversarial Defense

39 papers with code ยท Adversarial

State-of-the-art leaderboards

Latest papers without code

Adversarial Defense by Suppressing High-frequency Components

19 Aug 2019

Recent works show that deep neural networks trained on image classification dataset bias towards textures.

ADVERSARIAL DEFENSE IMAGE CLASSIFICATION

Comment on "Adv-BNN: Improved Adversarial Defense through Robust Bayesian Neural Network"

1 Jul 2019

A recent paper by Liu et al. combines the topics of adversarial training and Bayesian Neural Networks (BNN) and suggests that adversarially trained BNNs are more robust against adversarial attacks than their non-Bayesian counterparts.

ADVERSARIAL ATTACK ADVERSARIAL DEFENSE

Improved Adversarial Robustness via Logit Regularization Methods

10 Jun 2019

While great progress has been made at making neural networks effective across a wide range of visual tasks, most models are surprisingly vulnerable.

ADVERSARIAL DEFENSE

Defending against Adversarial Attacks through Resilient Feature Regeneration

8 Jun 2019

Deep neural network (DNN) predictions have been shown to be vulnerable to carefully crafted adversarial perturbations.

ADVERSARIAL DEFENSE

Adversarial Defense Through Network Profiling Based Path Extraction

CVPR 2019

Recently, researchers have started decomposing deep neural network models according to their semantics or functions.

ADVERSARIAL DEFENSE

AOGNets: Compositional Grammatical Architectures for Deep Learning

CVPR 2019

This paper presents deep compositional grammatical architectures which harness the best of two worlds: grammar models and DNNs.

ADVERSARIAL DEFENSE OBJECT DETECTION

Adversarial Defense by Stratified Convolutional Sparse Coding

CVPR 2019

We propose an adversarial defense method that achieves state-of-the-art performance among attack-agnostic adversarial defense methods while also maintaining robustness to input resolution, scale of adversarial perturbation, and scale of dataset size.

ADVERSARIAL DEFENSE

Adversarial Defense Framework for Graph Neural Network

9 May 2019

How to address the vulnerabilities and defense GNN against the adversarial attacks?

ADVERSARIAL DEFENSE GRAPH NEURAL NETWORK REPRESENTATION LEARNING

Benchmarking Neural Network Robustness to Common Corruptions and Perturbations

ICLR 2019

Then we propose a new dataset called ImageNet-P which enables researchers to benchmark a classifier's robustness to common perturbations.

ADVERSARIAL DEFENSE