sparse-rsSparse-RS: a versatile framework for query-efficient sparse black-box adversarial attacks
Stars: ✭ 24 (-73.03%)
procedural-advmlTask-agnostic universal black-box attacks on computer vision neural network via procedural noise (CCS'19)
Stars: ✭ 47 (-47.19%)
POPQORNAn Algorithm to Quantify Robustness of Recurrent Neural Networks
Stars: ✭ 44 (-50.56%)
DiagnoseRESource code and dataset for the CCKS201 paper "On Robustness and Bias Analysis of BERT-based Relation Extraction"
Stars: ✭ 23 (-74.16%)
TIGERPython toolbox to evaluate graph vulnerability and robustness (CIKM 2021)
Stars: ✭ 103 (+15.73%)
domain-shift-robustnessCode for the paper "Addressing Model Vulnerability to Distributional Shifts over Image Transformation Sets", ICCV 2019
Stars: ✭ 22 (-75.28%)
s-attack[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?".
Stars: ✭ 51 (-42.7%)
SimP-GCNImplementation of the WSDM 2021 paper "Node Similarity Preserving Graph Convolutional Networks"
Stars: ✭ 43 (-51.69%)
perceptual-advexCode and data for the ICLR 2021 paper "Perceptual Adversarial Robustness: Defense Against Unseen Threat Models".
Stars: ✭ 44 (-50.56%)
AWPCodes for NeurIPS 2020 paper "Adversarial Weight Perturbation Helps Robust Generalization"
Stars: ✭ 114 (+28.09%)
Attack-ImageNetNo.2 solution of Tianchi ImageNet Adversarial Attack Challenge.
Stars: ✭ 41 (-53.93%)
chopCHOP: An optimization library based on PyTorch, with applications to adversarial examples and structured neural network training.
Stars: ✭ 68 (-23.6%)
ATMC[NeurIPS'2019] Shupeng Gui, Haotao Wang, Haichuan Yang, Chen Yu, Zhangyang Wang, Ji Liu, “Model Compression with Adversarial Robustness: A Unified Optimization Framework”
Stars: ✭ 41 (-53.93%)
PGD-pytorchA pytorch implementation of "Towards Deep Learning Models Resistant to Adversarial Attacks"
Stars: ✭ 83 (-6.74%)
FLAT[ICCV2021 Oral] Fooling LiDAR by Attacking GPS Trajectory
Stars: ✭ 52 (-41.57%)
DUNCode for "Depth Uncertainty in Neural Networks" (https://arxiv.org/abs/2006.08437)
Stars: ✭ 65 (-26.97%)
cycle-confusionCode and models for ICCV2021 paper "Robust Object Detection via Instance-Level Temporal Cycle Confusion".
Stars: ✭ 67 (-24.72%)
CIL-ReIDBenchmarks for Corruption Invariant Person Re-identification. [NeurIPS 2021 Track on Datasets and Benchmarks]
Stars: ✭ 71 (-20.22%)
advrankAdversarial Ranking Attack and Defense, ECCV, 2020.
Stars: ✭ 19 (-78.65%)
belayRobust error-handling for Kotlin and Android
Stars: ✭ 35 (-60.67%)
code-soupThis is a collection of algorithms and approaches used in the book adversarial deep learning
Stars: ✭ 18 (-79.78%)
denoised-smoothingProvably defending pretrained classifiers including the Azure, Google, AWS, and Clarifai APIs
Stars: ✭ 82 (-7.87%)
aileen-coreSensor data aggregation tool for any numerical sensor data. Robust and privacy-friendly.
Stars: ✭ 15 (-83.15%)
gans-in-action"GAN 인 액션"(한빛미디어, 2020)의 코드 저장소입니다.
Stars: ✭ 29 (-67.42%)
adversarial-robustness-publicCode for AAAI 2018 accepted paper: "Improving the Adversarial Robustness and Interpretability of Deep Neural Networks by Regularizing their Input Gradients"
Stars: ✭ 49 (-44.94%)
shortcut-perspectiveFigures & code from the paper "Shortcut Learning in Deep Neural Networks" (Nature Machine Intelligence 2020)
Stars: ✭ 67 (-24.72%)
hyper-enginePython library for Bayesian hyper-parameters optimization
Stars: ✭ 80 (-10.11%)
geometric advGeometric Adversarial Attacks and Defenses on 3D Point Clouds (3DV 2021)
Stars: ✭ 20 (-77.53%)
generative adversaryCode for the unrestricted adversarial examples paper (NeurIPS 2018)
Stars: ✭ 58 (-34.83%)
trojanzooTrojanZoo provides a universal pytorch platform to conduct security researches (especially backdoor attacks/defenses) of image classification in deep learning.
Stars: ✭ 178 (+100%)
GeFsGenerative Forests in Python
Stars: ✭ 23 (-74.16%)
hard-label-attackNatural Language Attacks in a Hard Label Black Box Setting.
Stars: ✭ 26 (-70.79%)
robustness-vitContains code for the paper "Vision Transformers are Robust Learners" (AAAI 2022).
Stars: ✭ 78 (-12.36%)
KitanaQAKitanaQA: Adversarial training and data augmentation for neural question-answering models
Stars: ✭ 58 (-34.83%)
safe-control-gymPyBullet CartPole and Quadrotor environments—with CasADi symbolic a priori dynamics—for learning-based control and RL
Stars: ✭ 272 (+205.62%)
ijcnn19attacksAdversarial Attacks on Deep Neural Networks for Time Series Classification
Stars: ✭ 57 (-35.96%)
flowattackAttacking Optical Flow (ICCV 2019)
Stars: ✭ 58 (-34.83%)
AdvPCAdvPC: Transferable Adversarial Perturbations on 3D Point Clouds (ECCV 2020)
Stars: ✭ 35 (-60.67%)
robust-gcnImplementation of the paper "Certifiable Robustness and Robust Training for Graph Convolutional Networks".
Stars: ✭ 35 (-60.67%)
Robust-Semantic-SegmentationDynamic Divide-and-Conquer Adversarial Training for Robust Semantic Segmentation (ICCV2021)
Stars: ✭ 25 (-71.91%)
FeatureScatterFeature Scattering Adversarial Training
Stars: ✭ 64 (-28.09%)
Denoised-Smoothing-TFMinimal implementation of Denoised Smoothing (https://arxiv.org/abs/2003.01908) in TensorFlow.
Stars: ✭ 19 (-78.65%)
Generalization-Causality关于domain generalization,domain adaptation,causality,robutness,prompt,optimization,generative model各式各样研究的阅读笔记
Stars: ✭ 482 (+441.57%)
Pro-GNNImplementation of the KDD 2020 paper "Graph Structure Learning for Robust Graph Neural Networks"
Stars: ✭ 202 (+126.97%)
adversarial-recommender-systems-surveyThe 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-…
Stars: ✭ 110 (+23.6%)
humpdayElo ratings for global black box derivative-free optimizers
Stars: ✭ 94 (+5.62%)
RaySRayS: A Ray Searching Method for Hard-label Adversarial Attack (KDD2020)
Stars: ✭ 43 (-51.69%)
nn robustness analysisPython tools for analyzing the robustness properties of neural networks (NNs) from MIT ACL
Stars: ✭ 36 (-59.55%)
eleanorCode used during my Chaos Engineering and Resiliency Patterns talk.
Stars: ✭ 14 (-84.27%)