Browse > Adversarial > Adversarial Defense

Adversarial Defense

46 papers with code ยท Adversarial

Leaderboards

Latest papers without code

Defensive Tensorization: Randomized Tensor Parametrization for Robust Neural Networks

ICLR 2020

As deep neural networks become widely adopted for solving most problems in computer vision and audio-understanding, there are rising concerns about their potential vulnerability.

ADVERSARIAL DEFENSE AUDIO CLASSIFICATION IMAGE CLASSIFICATION

Simple and Effective Stochastic Neural Networks

ICLR 2020

Stochastic neural networks (SNNs) are currently topical, with several paradigms being actively investigated including dropout, Bayesian neural networks, variational information bottleneck (VIB) and noise regularized learning.

ADVERSARIAL ATTACK ADVERSARIAL DEFENSE

Instance adaptive adversarial training: Improved accuracy tradeoffs in neural nets

ICLR 2020

Adversarial training is by far the most successful strategy for improving robustness of neural networks to adversarial attacks.

ADVERSARIAL DEFENSE

Enhancing Adversarial Defense by k-Winners-Take-All

ICLR 2020

In all cases, the robustness of k-WTA networks outperforms that of traditional networks under white-box attacks.

ADVERSARIAL DEFENSE

MimicGAN: Robust Projection onto Image Manifolds with Corruption Mimicking

16 Dec 2019

However, PGD is a brittle optimization technique that fails to identify the right projection (or latent vector) when the observation is corrupted, or perturbed even by a small amount.

ADVERSARIAL DEFENSE ANOMALY DETECTION DATA AUGMENTATION DOMAIN ADAPTATION

Error Correcting Output Codes Improve Probability Estimation and Adversarial Robustness of Deep Neural Networks

NeurIPS 2019

Modern machine learning systems are susceptible to adversarial examples; inputs which clearly preserve the characteristic semantics of a given class, but whose classification is (usually confidently) incorrect.

ADVERSARIAL DEFENSE QUANTIZATION

Defensive Few-shot Adversarial Learning

16 Nov 2019

In this paper, instead of assuming such a distribution consistency, we propose to make this assumption at a task-level in the episodic training paradigm in order to better transfer the defense knowledge.

ADVERSARIAL DEFENSE FEW-SHOT LEARNING

GraphDefense: Towards Robust Graph Convolutional Networks

11 Nov 2019

Inspired by the previous works on adversarial defense for deep neural networks, and especially adversarial training algorithm, we propose a method called GraphDefense to defend against the adversarial perturbations.

ADVERSARIAL DEFENSE

Adversarial Defense Via Local Flatness Regularization

27 Oct 2019

In this paper, we define the local flatness of the loss surface as the maximum value of the chosen norm of the gradient regarding to the input within a neighborhood centered on the benign sample, and discuss the relationship between the local flatness and adversarial vulnerability.

ADVERSARIAL DEFENSE

Enforcing Linearity in DNN succours Robustness and Adversarial Image Generation

17 Oct 2019

Recent studies on the adversarial vulnerability of neural networks have shown that models trained with the objective of minimizing an upper bound on the worst-case loss over all possible adversarial perturbations improve robustness against adversarial attacks.

ADVERSARIAL DEFENSE IMAGE GENERATION REPRESENTATION LEARNING