Browse > Adversarial > Adversarial Defense

Adversarial Defense

19 papers with code · Adversarial

State-of-the-art leaderboards

No evaluation results yet. Help compare methods by submit evaluation metrics.

Latest papers with code

Certified Adversarial Robustness via Randomized Smoothing

8 Feb 2019locuslab/smoothing

Recent work has shown that any classifier which classifies well under Gaussian noise can be leveraged to create a new classifier that is provably robust to adversarial perturbations in L2 norm. In this work we provide the first tight analysis of this "randomized smoothing" technique.

ADVERSARIAL DEFENSE

08 Feb 2019

Image Super-Resolution as a Defense Against Adversarial Attacks

7 Jan 2019aamir-mustafa/super-resolution-adversarial-defense

Convolutional Neural Networks have achieved significant success across multiple computer vision tasks. The proposed scheme is simple and has the following advantages: (1) it does not require any model training or parameter optimization, (2) it complements other existing defense mechanisms, (3) it is agnostic to the attacked model and attack type and (4) it provides superior performance across all popular attack algorithms.

ADVERSARIAL DEFENSE IMAGE ENHANCEMENT IMAGE RESTORATION IMAGE SUPER-RESOLUTION

07 Jan 2019

Feature Denoising for Improving Adversarial Robustness

9 Dec 2018facebookresearch/ImageNet-Adversarial-Training

This study suggests that adversarial perturbations on images lead to noise in the features constructed by these networks. Motivated by this observation, we develop new network architectures that increase adversarial robustness by performing feature denoising.

ADVERSARIAL ATTACK ADVERSARIAL DEFENSE IMAGE CLASSIFICATION

Adversarial Defense of Image Classification Using a Variational Auto-Encoder

7 Dec 2018Roy-YL/VAE-Adversarial-Defense

Deep neural networks are known to be vulnerable to adversarial attacks. This exposes them to potential exploits in security-sensitive applications and highlights their lack of robustness.

ADVERSARIAL DEFENSE IMAGE CLASSIFICATION

07 Dec 2018

Efficient Formal Safety Analysis of Neural Networks

NeurIPS 2018 tcwangshiqi-columbia/Interval-Attack

Thus, there is an urgent need for formal analysis systems that can rigorously check neural networks for violations of different safety properties such as robustness against adversarial perturbations within a certain $L$-norm of a given image. Our approach can check different safety properties and find concrete counterexamples for networks that are 10$\times$ larger than the ones supported by existing analysis techniques.

ADVERSARIAL ATTACK ADVERSARIAL DEFENSE AUTONOMOUS DRIVING MALWARE DETECTION

19 Sep 2018

A Game-Based Approximate Verification of Deep Neural Networks with Provable Guarantees

10 Jul 2018TrustAI/DeepGame

In this paper, we study two variants of pointwise robustness, the maximum safe radius problem, which for a given input sample computes the minimum distance to an adversarial example, and the feature robustness problem, which aims to quantify the robustness of individual features to adversarial perturbations. While the second player aims to minimise the distance to an adversarial example, depending on the optimisation objective the first player can be cooperative or competitive.

ADVERSARIAL ATTACK ADVERSARIAL DEFENSE SELF-DRIVING CARS TRAFFIC SIGN RECOGNITION

10 Jul 2018

Benchmarking Neural Network Robustness to Common Corruptions and Perturbations

ICLR 2019 hendrycks/robustness

In this paper we establish rigorous benchmarks for image classifier robustness. Then we propose a new dataset called ImageNet-P which enables researchers to benchmark a classifier's robustness to common perturbations.

ADVERSARIAL DEFENSE

04 Jul 2018

Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples

ICML 2018 anishathalye/obfuscated-gradients

We identify obfuscated gradients, a kind of gradient masking, as a phenomenon that leads to a false sense of security in defenses against adversarial examples. While defenses that cause obfuscated gradients appear to defeat iterative optimization-based attacks, we find defenses relying on this effect can be circumvented.

ADVERSARIAL ATTACK ADVERSARIAL DEFENSE

Certified Defenses against Adversarial Examples

ICLR 2018 vtjeng/MIPVerify.jl

While neural networks have achieved high accuracy on standard image classification benchmarks, their accuracy drops to nearly zero in the presence of small adversarial perturbations to test inputs. Defenses based on regularization and adversarial training have been proposed, but often followed by new, stronger attacks that defeat these defenses.

ADVERSARIAL ATTACK ADVERSARIAL DEFENSE IMAGE CLASSIFICATION

29 Jan 2018