50 Open source projects that are alternatives of or similar to domain-shift-robustness

Sparse-RS: a versatile framework for query-efficient sparse black-box adversarial attacks

Codes for NeurIPS 2020 paper "Adversarial Weight Perturbation Helps Robust Generalization"

Task-agnostic universal black-box attacks on computer vision neural network via procedural noise (CCS'19)

KitanaQA: Adversarial training and data augmentation for neural question-answering models

Square Attack: a query-efficient black-box adversarial attack via random search [ECCV 2020]

Paper list of Adversarial Examples

Python tools for analyzing the robustness properties of neural networks (NNs) from MIT ACL

Adversarial Ranking Attack and Defense, ECCV, 2020.

Robust Out-of-distribution Detection in Neural Networks

Adversarial Distributional Training (NeurIPS 2020)

Consistency Regularization for Adversarial Robustness (AAAI 2022)

Code for the AAAI 2022 publication "Well-classified Examples are Underestimated in Classification with Deep Neural Networks"

Source code and dataset for the CCKS201 paper "On Robustness and Bias Analysis of BERT-based Relation Extraction"

Dynamic Divide-and-Conquer Adversarial Training for Robust Semantic Segmentation （ICCV2021）

Code for EMNLP-IJCNLP 2019 MRQA Workshop Paper: "Domain-agnostic Question-Answering with Adversarial Training"

Code and data for the ICLR 2021 paper "Perceptual Adversarial Robustness: Defense Against Unseen Threat Models".

Reimplementing cool papers in PyTorch...

Foofah: programming-by-example data transformation program synthesizer

[CVPR 2022] S-attack library. Official implementation of two papers "Vehicle trajectory prediction works, but not everywhere" and "Are socially-aware trajectory prediction models really socially-aware?".

Language-Adversarial Training for Cross-Lingual Text Classification (TACL)

No.2 solution of Tianchi ImageNet Adversarial Attack Challenge.

Adversarial Attacks on Deep Neural Networks for Time Series Classification

This is a collection of algorithms and approaches used in the book adversarial deep learning

"GAN 인 액션"(한빛미디어, 2020)의 코드 저장소입니다.

Feature Scattering Adversarial Training

The goal of this survey is two-fold: (i) to present recent advances on adversarial machine learning (AML) for the security of RS (i.e., attacking and defense recommendation models), (ii) to show another successful application of AML in generative adversarial networks (GANs) for generative applications, thanks to their ability for learning (high-…

Code for paper "Model-based Adversarial Meta-Reinforcement Learning" (https://arxiv.org/abs/2006.08875)

Benchmarks for semi-supervised domain generalization.

Python toolbox to evaluate graph vulnerability and robustness (CIKM 2021)

[CVPR2021] Meta Batch-Instance Normalization for Generalizable Person Re-Identification

A pytorch implementation of "Towards Deep Learning Models Resistant to Adversarial Attacks"

[ICCV2021 Oral] Fooling LiDAR by Attacking GPS Trajectory

TrojanZoo provides a universal pytorch platform to conduct security researches (especially backdoor attacks/defenses) of image classification in deep learning.

CHOP: An optimization library based on PyTorch, with applications to adversarial examples and structured neural network training.

Natural Language Attacks in a Hard Label Black Box Setting.

Code for the paper: Adversarial Training Against Location-Optimized Adversarial Patches. ECCV-W 2020.

Attacking Optical Flow (ICCV 2019)

AdvPC: Transferable Adversarial Perturbations on 3D Point Clouds (ECCV 2020)

An Algorithm to Quantify Robustness of Recurrent Neural Networks

Geometric Adversarial Attacks and Defenses on 3D Point Clouds (3DV 2021)

Code for the unrestricted adversarial examples paper (NeurIPS 2018)

Implementation of the WSDM 2021 paper "Node Similarity Preserving Graph Convolutional Networks"

Implementation of the KDD 2020 paper "Graph Structure Learning for Robust Graph Neural Networks"

No description or website provided.

Graph Robustness Benchmark: A scalable, unified, modular, and reproducible benchmark for evaluating the adversarial robustness of Graph Machine Learning.

Adversarial Robustness Toolbox (ART) - Python Library for Machine Learning Security - Evasion, Poisoning, Extraction, Inference - Red and Blue Teams

A Python toolbox to create adversarial examples that fool neural networks in PyTorch, TensorFlow, and JAX

Data augmentation for NLP

[EMNLP 2020] "T3: Tree-Autoencoder Constrained Adversarial Text Generation for Targeted Attack" by Boxin Wang, Hengzhi Pei, Boyuan Pan, Qian Chen, Shuohang Wang, Bo Li

Transfer learning / domain adaptation / domain generalization / multi-task learning etc. Papers, codes, datasets, applications, tutorials.-迁移学习