71 Open source projects that are alternatives of or similar to s-attack

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

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

An Algorithm to Quantify Robustness of Recurrent Neural Networks

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

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

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

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

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

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

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

关于domain generalization，domain adaptation，causality，robutness，prompt，optimization，generative model各式各样研究的阅读笔记

Code for "Depth Uncertainty in Neural Networks" (https://arxiv.org/abs/2006.08437)

Social Ways: Learning Multi-Modal Distributions of Pedestrian Trajectories with GANs (CVPR 2019)

阿里云MNS

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

Code for the unrestricted adversarial examples paper (NeurIPS 2018)

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

No description or website provided.

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

Pre-Training Buys Better Robustness and Uncertainty Estimates (ICML 2019)

Adversarial Attacks on Deep Neural Networks for Time Series Classification

Code repo for realtime multi-person pose estimation in CVPR'17 (Oral)

Reachability analysis for closed-loop control systems

PyTorch Implementation of Google's Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions. This implementation supports both single-, multi-speaker TTS and several techniques to enforce the robustness and efficiency of the model.

Generative Forests in Python

Code for NeurIPS 2019 Paper

Benchmarks for Corruption Invariant Person Re-identification. [NeurIPS 2021 Track on Datasets and Benchmarks]

Adversarial Distributional Training (NeurIPS 2020)

Code for AAAI 2018 accepted paper: "Improving the Adversarial Robustness and Interpretability of Deep Neural Networks by Regularizing their Input Gradients"

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

"GAN 인 액션"(한빛미디어, 2020)의 코드 저장소입니다.

[ICCV2021 Oral] Fooling LiDAR by Attacking GPS Trajectory

Minimal implementation of Denoised Smoothing (https://arxiv.org/abs/2003.01908) in TensorFlow.

Code and models for ICCV2021 paper "Robust Object Detection via Instance-Level Temporal Cycle Confusion".

A curated (most recent) list of resources for Learning with Noisy Labels

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

[NeurIPS 2021]: Are Transformers More Robust Than CNNs? (Pytorch implementation & checkpoints)

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-…

(ICML 2022) Official PyTorch implementation of “Blurs Behave Like Ensembles: Spatial Smoothings to Improve Accuracy, Uncertainty, and Robustness”.

Natural Language Attacks in a Hard Label Black Box Setting.

Recentrifuge: robust comparative analysis and contamination removal for metagenomics

No.2 solution of Tianchi ImageNet Adversarial Attack Challenge.

OpenPose: Real-time multi-person keypoint detection library for body, face, hands, and foot estimation

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

Realtime Multi-Person Pose Estimation data server. Used as a training and validation data provider in training process.

Code used during my Chaos Engineering and Resiliency Patterns talk.

Robust error-handling for Kotlin and Android

PyBullet CartPole and Quadrotor environments—with CasADi symbolic a priori dynamics—for learning-based control and RL

NIPS Adversarial Vision Challenge

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

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

RayS: A Ray Searching Method for Hard-label Adversarial Attack (KDD2020)

Attacking Optical Flow (ICCV 2019)

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

Sensor data aggregation tool for any numerical sensor data. Robust and privacy-friendly.

Figures & code from the paper "Shortcut Learning in Deep Neural Networks" (Nature Machine Intelligence 2020)

Contains code for the paper "Vision Transformers are Robust Learners" (AAAI 2022).

A Closer Look at Accuracy vs. Robustness

[NeurIPS'2019] Shupeng Gui, Haotao Wang, Haichuan Yang, Chen Yu, Zhangyang Wang, Ji Liu, “Model Compression with Adversarial Robustness: A Unified Optimization Framework”

Implementation of the paper "Certifiable Robustness and Robust Training for Graph Convolutional Networks".