About

An Adversarial Attack is a technique to find a perturbation that changes the prediction of a machine learning model. The perturbation can be very small and imperceptible to human eyes.

Source: Recurrent Attention Model with Log-Polar Mapping is Robust against Adversarial Attacks

Benchmarks

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

Subtasks

Datasets

Greatest papers with code

Technical Report on the CleverHans v2.1.0 Adversarial Examples Library

3 Oct 2016openai/cleverhans

An adversarial example library for constructing attacks, building defenses, and benchmarking both

ADVERSARIAL ATTACK ADVERSARIAL DEFENSE

The Limitations of Deep Learning in Adversarial Settings

24 Nov 2015cleverhans-lab/cleverhans

In this work, we formalize the space of adversaries against deep neural networks (DNNs) and introduce a novel class of algorithms to craft adversarial samples based on a precise understanding of the mapping between inputs and outputs of DNNs.

ADVERSARIAL ATTACK ADVERSARIAL DEFENSE

Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural Networks

3 Oct 2019jacobgil/pytorch-grad-cam

Recently, increasing attention has been drawn to the internal mechanisms of convolutional neural networks, and the reason why the network makes specific decisions.

ADVERSARIAL ATTACK DECISION MAKING FAIRNESS

Foolbox: A Python toolbox to benchmark the robustness of machine learning models

13 Jul 2017bethgelab/foolbox

Foolbox is a new Python package to generate such adversarial perturbations and to quantify and compare the robustness of machine learning models.

ADVERSARIAL ATTACK

Adversarial Examples on Graph Data: Deep Insights into Attack and Defense

5 Mar 2019stellargraph/stellargraph

Based on this observation, we propose a defense approach which inspects the graph and recovers the potential adversarial perturbations.

ADVERSARIAL ATTACK ADVERSARIAL DEFENSE

TextAttack: A Framework for Adversarial Attacks, Data Augmentation, and Adversarial Training in NLP

29 Apr 2020QData/TextAttack

TextAttack also includes data augmentation and adversarial training modules for using components of adversarial attacks to improve model accuracy and robustness.

ADVERSARIAL ATTACK ADVERSARIAL TEXT DATA AUGMENTATION LEXICAL ENTAILMENT MACHINE TRANSLATION TEXT CLASSIFICATION

BERT-ATTACK: Adversarial Attack Against BERT Using BERT

EMNLP 2020 QData/TextAttack

Adversarial attacks for discrete data (such as texts) have been proved significantly more challenging than continuous data (such as images) since it is difficult to generate adversarial samples with gradient-based methods.

ADVERSARIAL ATTACK

BAE: BERT-based Adversarial Examples for Text Classification

EMNLP 2020 QData/TextAttack

Modern text classification models are susceptible to adversarial examples, perturbed versions of the original text indiscernible by humans which get misclassified by the model.

ADVERSARIAL ATTACK ADVERSARIAL TEXT TEXT CLASSIFICATION

A Little Fog for a Large Turn

16 Jan 2020SullyChen/Autopilot-TensorFlow

Small, carefully crafted perturbations called adversarial perturbations can easily fool neural networks.

ADVERSARIAL ATTACK AUTONOMOUS NAVIGATION SAFETY PERCEPTION RECOGNITION

Attacking and Defending Machine Learning Applications of Public Cloud

27 Jul 2020advboxes/AdvBox

Adversarial attack breaks the boundaries of traditional security defense.

ADVERSARIAL ATTACK