Browse > Adversarial > Adversarial Defense

Adversarial Defense

39 papers with code · Adversarial

State-of-the-art leaderboards

Latest papers with code

Provably Robust Deep Learning via Adversarially Trained Smoothed Classifiers

9 Jun 2019Hadisalman/smoothing-adversarial

Recent works have shown the effectiveness of randomized smoothing as a scalable technique for building neural network-based classifiers that are provably robust to $\ell_2$-norm adversarial perturbations.

ADVERSARIAL ATTACK ADVERSARIAL DEFENSE

82
09 Jun 2019

Adversarial Examples for Non-Parametric Methods: Attacks, Defenses and Large Sample Limits

7 Jun 2019yangarbiter/adversarial-nonparametrics

Adversarial examples have received a great deal of recent attention because of their potential to uncover security flaws in machine learning systems.

ADVERSARIAL ATTACK ADVERSARIAL DEFENSE

10
07 Jun 2019

Decoupling Direction and Norm for Efficient Gradient-Based L2 Adversarial Attacks and Defenses

CVPR 2019 jeromerony/fast_adversarial

Research on adversarial examples in computer vision tasks has shown that small, often imperceptible changes to an image can induce misclassification, which has security implications for a wide range of image processing systems.

ADVERSARIAL ATTACK ADVERSARIAL DEFENSE

73
01 Jun 2019

Scaleable input gradient regularization for adversarial robustness

27 May 2019cfinlay/tulip

Input gradient regularization is not thought to be an effective means for promoting adversarial robustness.

ADVERSARIAL ATTACK ADVERSARIAL DEFENSE

12
27 May 2019

Resisting Adversarial Attacks by $k$-Winners-Take-All

25 May 2019a554b554/kWTA-Activation

We propose a simple change to the current neural network structure for defending against gradient-based adversarial attacks.

ADVERSARIAL DEFENSE

4
25 May 2019

Privacy Risks of Securing Machine Learning Models against Adversarial Examples

24 May 2019lwsong/privacy-vs-robustness

Our experimental evaluation demonstrates that compared with the natural training (undefended) approach, adversarial defense methods can indeed increase the target model's risk against membership inference attacks.

ADVERSARIAL DEFENSE

0
24 May 2019

You Only Propagate Once: Accelerating Adversarial Training via Maximal Principle

2 May 2019a1600012888/YOPO-You-Only-Propagate-Once

In this paper, we show that adversarial training can be cast as a discrete time differential game.

ADVERSARIAL DEFENSE

77
02 May 2019

Adversarial Training for Free!

29 Apr 2019a1600012888/YOPO-You-Only-Propagate-Once

Adversarial training, in which a network is trained on adversarial examples, is one of the few defenses against adversarial attacks that withstands strong attacks.

ADVERSARIAL ATTACK ADVERSARIAL DEFENSE

77
29 Apr 2019

Adversarial Defense by Restricting the Hidden Space of Deep Neural Networks

1 Apr 2019aamir-mustafa/pcl-adversarial-defense

Deep neural networks are vulnerable to adversarial attacks, which can fool them by adding minuscule perturbations to the input images.

ADVERSARIAL DEFENSE

10
01 Apr 2019

A Provable Defense for Deep Residual Networks

29 Mar 2019eth-sri/diffai

We present a training system, which can provably defend significantly larger neural networks than previously possible, including ResNet-34 and DenseNet-100.

ADVERSARIAL DEFENSE

138
29 Mar 2019