GitHub topics: adversarial-robustness

Repositories

ky295/reasoning-manipulation

Adversarial Manipulation of CoT

Language: Jupyter Notebook - Size: 407 MB - Last synced at: 4 days ago - Pushed at: 4 days ago - Stars: 2 - Forks: 0

hxxdtd/Awesome-Diffusion-Model-Unlearning

A repository of resources on machine unlearning for diffusion models

Size: 19.5 KB - Last synced at: 8 days ago - Pushed at: 8 days ago - Stars: 30 - Forks: 0

chilljudaoren/A-Survey-of-Adversarial-Attack

A curated collection of resources, papers, code, and benchmarks on adversarial attacks and robustness evaluation for vision-language models (VLMs).

Size: 35.2 KB - Last synced at: 9 days ago - Pushed at: 9 days ago - Stars: 0 - Forks: 0

RobustBench/robustbench

RobustBench: a standardized adversarial robustness benchmark [NeurIPS 2021 Benchmarks and Datasets Track]

Language: Python - Size: 5.92 MB - Last synced at: 7 days ago - Pushed at: 3 months ago - Stars: 720 - Forks: 100

pralab/robustness-congruent-advtrain

Language: Python - Size: 516 KB - Last synced at: 16 days ago - Pushed at: 16 days ago - Stars: 1 - Forks: 0

Our Conflict-aware Evidential Deep Learning (C-EDL) method enhances robustness to OOD and adversarial inputs by combining evidence from metamorphic transformations and reducing evidence when conflicts arise, signalling higher uncertainty.

Language: Python - Size: 567 KB - Last synced at: 23 days ago - Pushed at: 23 days ago - Stars: 0 - Forks: 0

fra31/auto-attack

Code relative to "Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks"

Language: Python - Size: 39.7 MB - Last synced at: 23 days ago - Pushed at: about 1 year ago - Stars: 705 - Forks: 120

jiequancui/DKL

Decoupled Kullback-Leibler Divergence Loss (DKL), NeurIPS 2024 / Generalized Kullback-Leibler Divergence Loss (GKL)

Language: Python - Size: 14.8 MB - Last synced at: 28 days ago - Pushed at: 29 days ago - Stars: 44 - Forks: 4

zhyblue424/TGA-ZSR

(NeurIPS 2024)Text-Guided Attention is All You Need for Zero-Shot Robustness in Vision-Language Models

Language: Python - Size: 3.59 MB - Last synced at: 15 days ago - Pushed at: 3 months ago - Stars: 12 - Forks: 2

joseph-nagel/adversarial-ml

Adversarial attacks and defenses

Language: Jupyter Notebook - Size: 324 KB - Last synced at: about 2 months ago - Pushed at: about 2 months ago - Stars: 0 - Forks: 0

Yarinyl/KDAT

official implementation for the AAAI-2025 paper KDAT: Inherent Adversarial Robustness via Knowledge Distillation with Adversarial Tuning for Object Detection Models.

Language: Python - Size: 7.76 MB - Last synced at: about 2 months ago - Pushed at: about 2 months ago - Stars: 0 - Forks: 0

emaballarin/CARSO

👀🛡️ Code for the paper “Carefully Blending Adversarial Training and Purification Improves Adversarial Robustness” by Emanuele Ballarin, Alessio Ansuini and Luca Bortolussi (2024)

Language: Python - Size: 152 KB - Last synced at: about 2 months ago - Pushed at: about 2 months ago - Stars: 7 - Forks: 1

Skyress1/ECG-FAT-Code

Code for our paper "Mitigating Adversarial Attacks on ECG Classification in Federated Learning via Adversarial Training", Artificial Intelligence Theory and Applications.

Size: 6.84 KB - Last synced at: about 2 months ago - Pushed at: about 2 months ago - Stars: 0 - Forks: 0

alibaba/easyrobust

EasyRobust: an Easy-to-use library for state-of-the-art Robust Computer Vision Research with PyTorch.

Language: Jupyter Notebook - Size: 19 MB - Last synced at: about 2 months ago - Pushed at: 12 months ago - Stars: 332 - Forks: 38

adil-faiyaz98/neural-scope

A comprehensive tool for analyzing machine learning models with CI/CD integration. Features include pre-trained model support, security analysis, adversarial robustness, testing, model versioning and MLFlow integration

Language: Python - Size: 123 MB - Last synced at: about 1 month ago - Pushed at: 2 months ago - Stars: 1 - Forks: 0

faidrapts/randomized-smoothing-adv-sr

Randomized smoothing as an adversarial defense for inverse problems, applied to super-resolution, and compared to adversarial training.

Language: Jupyter Notebook - Size: 17.1 MB - Last synced at: 2 months ago - Pushed at: 2 months ago - Stars: 0 - Forks: 0

thu-ml/ares

A Python library for adversarial machine learning focusing on benchmarking adversarial robustness.

Language: Python - Size: 378 MB - Last synced at: about 1 month ago - Pushed at: over 1 year ago - Stars: 505 - Forks: 86

Harry24k/MAIR

Fantastic Robustness Measures: The Secrets of Robust Generalization [NeurIPS 2023]

Language: Python - Size: 274 KB - Last synced at: 3 months ago - Pushed at: 6 months ago - Stars: 38 - Forks: 6

IGITUGraz/OutputCodeMatching

Code for "Improving Robustness Against Stealthy Weight Bit-Flip Attacks by Output Code Matching" [CVPR 2022]

Language: Python - Size: 47.9 KB - Last synced at: 3 months ago - Pushed at: about 3 years ago - Stars: 6 - Forks: 1

ChoiDae1/robustify-T2I

[ECCV 2024 - Oral] Official PyTorch Implementation of "Adversarial Robustification via Text-to-Image Diffusion Models"

Language: Python - Size: 3.28 MB - Last synced at: 2 months ago - Pushed at: 11 months ago - Stars: 12 - Forks: 0

microsoft/denoised-smoothing

Provably defending pretrained classifiers including the Azure, Google, AWS, and Clarifai APIs

Language: Jupyter Notebook - Size: 21.6 MB - Last synced at: 3 days ago - Pushed at: about 4 years ago - Stars: 97 - Forks: 18

abhijay9/attacking_perceptual_similarity_metrics

[TMLR 2023] as a featured article (spotlight :star2: or top 0.01% of the accepted papers). In this study, we systematically examine the robustness of both traditional and learned perceptual similarity metrics to imperceptible adversarial perturbations.

Language: Python - Size: 1.8 MB - Last synced at: 5 months ago - Pushed at: 5 months ago - Stars: 6 - Forks: 2

suhyeok-jang/FT-CADIS

Code for the paper "Confidence-aware Denoised Fine-tuning of Off-the-shelf Models for Certified Robustness" (TMLR 2024)

Language: Python - Size: 189 KB - Last synced at: 6 months ago - Pushed at: 7 months ago - Stars: 10 - Forks: 0

VITA-Group/Adv-SS-Pretraining

[CVPR 2020] Adversarial Robustness: From Self-Supervised Pre-Training to Fine-Tuning

Language: Python - Size: 974 KB - Last synced at: 2 months ago - Pushed at: over 3 years ago - Stars: 85 - Forks: 13

cdluminate/robrank

Adversarial Attack and Defense in Deep Ranking, T-PAMI, 2024

Language: Python - Size: 435 KB - Last synced at: 3 months ago - Pushed at: over 1 year ago - Stars: 23 - Forks: 2

IGITUGraz/SparseAdversarialTraining

Code for "Training Adversarially Robust Sparse Networks via Bayesian Connectivity Sampling" [ICML 2021]

Language: Python - Size: 37.1 KB - Last synced at: 3 months ago - Pushed at: over 3 years ago - Stars: 10 - Forks: 1

fra31/robust-finetuning

Code relative to "Adversarial robustness against multiple and single $l_p$-threat models via quick fine-tuning of robust classifiers"

Language: Python - Size: 19.5 KB - Last synced at: about 2 months ago - Pushed at: over 2 years ago - Stars: 18 - Forks: 4

IGITUGraz/RobustSNNConversion

Code for "Adversarially Robust Spiking Neural Networks Through Conversion" [TMLR 2024]

Language: Python - Size: 29.3 KB - Last synced at: about 1 month ago - Pushed at: about 1 year ago - Stars: 3 - Forks: 0

Bai-YT/AdaptiveSmoothing

Implementation of the paper "Improving the Accuracy-Robustness Trade-off of Classifiers via Adaptive Smoothing".

Language: Jupyter Notebook - Size: 1.6 MB - Last synced at: 3 months ago - Pushed at: over 1 year ago - Stars: 11 - Forks: 0

myuito3/AdvGrads

The all-in-one tool for comprehensive experimentation with adversarial attacks on image recognition.

Language: Python - Size: 148 KB - Last synced at: 8 months ago - Pushed at: 8 months ago - Stars: 0 - Forks: 0

VITA-Group/Alleviate-Robust-Overfitting

[ICLR 2021] "Robust Overfitting may be mitigated by properly learned smoothening" by Tianlong Chen*, Zhenyu Zhang*, Sijia Liu, Shiyu Chang, Zhangyang Wang

Language: Python - Size: 646 KB - Last synced at: 2 months ago - Pushed at: over 3 years ago - Stars: 46 - Forks: 5

Bai-YT/MixedNUTS

MixedNUTS: Training-Free Accuracy-Robustness Balance via Nonlinearly Mixed Classifiers

Language: Python - Size: 717 KB - Last synced at: 10 months ago - Pushed at: 10 months ago - Stars: 4 - Forks: 0

VITA-Group/Aug-NeRF

[CVPR 2022] "Aug-NeRF: Training Stronger Neural Radiance Fields with Triple-Level Physically-Grounded Augmentations" by Tianlong Chen*, Peihao Wang*, Zhiwen Fan, Zhangyang Wang

Language: Python - Size: 205 KB - Last synced at: 2 months ago - Pushed at: about 3 years ago - Stars: 124 - Forks: 8

LayneH/self-adaptive-training

[TPAMI2022 & NeurIPS2020] Official implementation of Self-Adaptive Training

Language: Python - Size: 91.8 KB - Last synced at: 7 months ago - Pushed at: over 3 years ago - Stars: 127 - Forks: 23

mlosch/SAT

Official repository for the paper: "On Adversarial Training without Perturbing all Examples", Accepted at ICLR 2024

Language: Python - Size: 7.22 MB - Last synced at: 11 months ago - Pushed at: 11 months ago - Stars: 0 - Forks: 0

hylee817/datafreeshield

The official implementation of "DataFreeShield: Defending Adversarial Attacks without Training Data" accepted in ICML 2024.

Language: Python - Size: 1.53 MB - Last synced at: 11 months ago - Pushed at: 11 months ago - Stars: 3 - Forks: 0

imrahulr/hat

Helper-based Adversarial Training: Reducing Excessive Margin to Achieve a Better Accuracy vs. Robustness Trade-off

Language: Python - Size: 251 KB - Last synced at: 11 months ago - Pushed at: about 3 years ago - Stars: 29 - Forks: 5

zjysteven/DVERGE

[NeurIPS'20 Oral] DVERGE: Diversifying Vulnerabilities for Enhanced Robust Generation of Ensembles

Language: Python - Size: 24 MB - Last synced at: about 1 month ago - Pushed at: over 3 years ago - Stars: 55 - Forks: 13

zhichao-lu/robust-residual-network

Revisiting Residual Networks for Adversarial Robustness: An Architectural Perspective

Language: Python - Size: 2.64 MB - Last synced at: about 1 year ago - Pushed at: about 1 year ago - Stars: 19 - Forks: 4

Haichao-Zhang/FeatureScatter

Feature Scattering Adversarial Training (NeurIPS19)

Language: Python - Size: 16.6 KB - Last synced at: about 1 year ago - Pushed at: about 1 year ago - Stars: 71 - Forks: 11

XinyiYS/Robust-and-Fair-Federated-Learning

Implementing the algorithm from our paper: "A Reputation Mechanism Is All You Need: Collaborative Fairness and Adversarial Robustness in Federated Learning".

Language: Python - Size: 32.2 KB - Last synced at: about 1 year ago - Pushed at: about 1 year ago - Stars: 31 - Forks: 11

Verified-Intelligence/alpha-beta-CROWN

alpha-beta-CROWN: An Efficient, Scalable and GPU Accelerated Neural Network Verifier (winner of VNN-COMP 2021, 2022, and 2023)

Language: Python - Size: 70.4 MB - Last synced at: about 1 year ago - Pushed at: about 1 year ago - Stars: 202 - Forks: 46

VITA-Group/triple-wins

[ICLR 2020] ”Triple Wins: Boosting Accuracy, Robustness and Efficiency Together by Enabling Input-Adaptive Inference“

Language: Python - Size: 13.2 MB - Last synced at: 2 months ago - Pushed at: over 3 years ago - Stars: 24 - Forks: 7

AI4LIFE-GROUP/average-case-robustness

Characterizing Data Point Vulnerability via Average-Case Robustness, UAI 2024

Language: Python - Size: 38.9 MB - Last synced at: about 1 year ago - Pushed at: about 1 year ago - Stars: 0 - Forks: 0

ti1uan/simplex-CROWN

Uses the simplex to propose a tighter boundary for the l1 perturbation of the convex activation function network, improving the effect of the CROWN algorithm.

Language: Python - Size: 3.1 MB - Last synced at: 6 months ago - Pushed at: about 1 year ago - Stars: 1 - Forks: 0

VITA-Group/SparseADV_Homotopy

[ICML 2021 Long Talk] "Sparse and Imperceptible Adversarial Attack via a Homotopy Algorithm" by Mingkang Zhu, Tianlong Chen, Zhangyang Wang

Language: Python - Size: 604 KB - Last synced at: 22 days ago - Pushed at: over 3 years ago - Stars: 9 - Forks: 3

GATECH-EIC/NeRFool

[ICML 2023] "NeRFool: Uncovering the Vulnerability of Generalizable Neural Radiance Fields against Adversarial Perturbations" by Yonggan Fu, Ye Yuan, Souvik Kundu, Shang Wu, Shunyao Zhang, Yingyan (Celine) Lin

Language: Python - Size: 2.51 MB - Last synced at: about 1 year ago - Pushed at: over 1 year ago - Stars: 14 - Forks: 1

VITA-Group/LTH-Pass

[TMLR] "Can You Win Everything with Lottery Ticket?" by Tianlong Chen, Zhenyu Zhang, Jun Wu, Randy Huang, Sijia Liu, Shiyu Chang, Zhangyang Wang

Language: Python - Size: 8.54 MB - Last synced at: 2 months ago - Pushed at: almost 3 years ago - Stars: 10 - Forks: 2

sparshgup/Qu-TN

Enabling Adversarial Robustness in Variational Quantum Classifiers with Noisy Low-Rank Tensor Ring Approximation

Language: Python - Size: 9.77 KB - Last synced at: over 1 year ago - Pushed at: over 1 year ago - Stars: 0 - Forks: 0

fanghenshaometeor/DIversity-via-Orthogonality

Code for the paper "Towards Robust Neural Networks via Orthogonal Diversity"

Language: Python - Size: 938 KB - Last synced at: over 1 year ago - Pushed at: over 1 year ago - Stars: 2 - Forks: 0

GATECH-EIC/Patch-Fool

[ICLR 2022] "Patch-Fool: Are Vision Transformers Always Robust Against Adversarial Perturbations?" by Yonggan Fu, Shunyao Zhang, Shang Wu, Cheng Wan, Yingyan Lin

Language: Python - Size: 13.4 MB - Last synced at: about 1 year ago - Pushed at: over 3 years ago - Stars: 22 - Forks: 9

CN-TU/adversarial-recurrent-ids Fork of muxamilian/privacy-tuw

Contact: Alexander Hartl, Maximilian Bachl, Fares Meghdouri. Explainability methods and Adversarial Robustness metrics for RNNs for Intrusion Detection Systems. Also contains code for "SparseIDS: Learning Packet Sampling with Reinforcement Learning" (branch "rl").

Language: TeX - Size: 2.07 GB - Last synced at: about 1 year ago - Pushed at: over 4 years ago - Stars: 14 - Forks: 11

sayakpaul/par-cvpr-21 Fork of dipanjanS/adversarial-learning-robustness

Contains notebooks for the PAR tutorial at CVPR 2021.

Language: Jupyter Notebook - Size: 83.2 MB - Last synced at: 6 days ago - Pushed at: about 4 years ago - Stars: 36 - Forks: 8

eth-sri/smoothing-ensembles

[ICLR 2022] Boosting Randomized Smoothing with Variance Reduced Classifiers

Language: Python - Size: 26.4 KB - Last synced at: about 1 year ago - Pushed at: over 3 years ago - Stars: 10 - Forks: 1

max-andr/square-attack

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

Language: Python - Size: 12.5 MB - Last synced at: over 1 year ago - Pushed at: almost 5 years ago - Stars: 128 - Forks: 24

Ehyaei/Causal-Fair-Metric-Learning

This project Implements the paper “Causally Robust Fair Metric Learning: Bridging Causality, Individual Fairness, and Adversarial Robustness” using the Python language.

Language: Python - Size: 3.08 MB - Last synced at: over 1 year ago - Pushed at: over 1 year ago - Stars: 0 - Forks: 0

AI-secure/InfoBERT

[ICLR 2021] "InfoBERT: Improving Robustness of Language Models from An Information Theoretic Perspective" by Boxin Wang, Shuohang Wang, Yu Cheng, Zhe Gan, Ruoxi Jia, Bo Li, Jingjing Liu

Language: Python - Size: 72.3 KB - Last synced at: over 1 year ago - Pushed at: over 1 year ago - Stars: 81 - Forks: 6

cemanil/LNets

Lipschitz Neural Networks described in "Sorting Out Lipschitz Function Approximation" (ICML 2019).

Language: Python - Size: 72.3 KB - Last synced at: over 1 year ago - Pushed at: about 5 years ago - Stars: 50 - Forks: 20

samuel930930/Dual-Manifold-Adversarial-Training

[NeurIPS2020] The official repository of "Dual Manifold Adversarial Robustness: Defense against Lp and non-Lp Adversarial Attacks".

Language: Python - Size: 155 KB - Last synced at: almost 2 years ago - Pushed at: about 4 years ago - Stars: 8 - Forks: 1

ginevracoal/adversarial_examples

Random Projections for improved Adversarial Robustness

Language: Jupyter Notebook - Size: 1.23 GB - Last synced at: almost 2 years ago - Pushed at: about 5 years ago - Stars: 2 - Forks: 0

yangarbiter/interpretable-robust-trees

Connecting Interpretability and Robustness in Decision Trees through Separation

Language: Jupyter Notebook - Size: 1.78 MB - Last synced at: almost 2 years ago - Pushed at: about 4 years ago - Stars: 13 - Forks: 0

MKYucel/adversarial_robustness_zsl

[ECCV 2020 AROW Workshop] A Deep Dive into Adversarial Robustness in Zero-Shot Learning

Language: Python - Size: 7.52 MB - Last synced at: almost 2 years ago - Pushed at: over 3 years ago - Stars: 6 - Forks: 0

lafeat/lafeat

LAFEAT: Piercing Through Adversarial Defenses with Latent Features (CVPR 2021 Oral)

Language: Python - Size: 34.4 MB - Last synced at: almost 2 years ago - Pushed at: about 4 years ago - Stars: 16 - Forks: 3

rrmhearts/adversarial-manipulated-geometry Fork of pankessel/explanations_can_be_manipulated

implementation for "Overcoming Adversarial Attacks for HITL Applications"

Language: Python - Size: 17.6 MB - Last synced at: almost 2 years ago - Pushed at: almost 2 years ago - Stars: 0 - Forks: 0

sigeisler/reliable_gnn_via_robust_aggregation

This repository contains the official implementation of the paper "Reliable Graph Neural Networks via Robust Aggregation" (NeurIPS, 2020).

Language: Python - Size: 309 MB - Last synced at: about 2 years ago - Pushed at: over 3 years ago - Stars: 14 - Forks: 3

zbh2047/L_inf-dist-net-v2

[ICLR 2022] Training L_inf-dist-net with faster acceleration and better training strategies

Language: Cuda - Size: 298 KB - Last synced at: about 2 years ago - Pushed at: over 3 years ago - Stars: 16 - Forks: 3

zbh2047/L_inf-dist-net

[ICML 2021] This is the official github repo for training L_inf dist nets with high certified accuracy.

Language: Python - Size: 56.6 KB - Last synced at: about 2 years ago - Pushed at: over 3 years ago - Stars: 37 - Forks: 6

alexklwong/targeted-adversarial-perturbations-monocular-depth

PyTorch implementation of Targeted Adversarial Perturbations for Monocular Depth Predictions (in NeurIPS 2020)

Language: HTML - Size: 29 MB - Last synced at: about 2 years ago - Pushed at: over 2 years ago - Stars: 12 - Forks: 3

VITA-Group/CIL-QUD

[TMLR 22] "Queried Unlabeled Data Improves and Robustifies Class- Incremental Learning" by Tianlong Chen, Sijia Liu, Shiyu Chang, Lisa Animi, Zhangyang Wang

Size: 2.93 KB - Last synced at: 3 months ago - Pushed at: about 3 years ago - Stars: 3 - Forks: 0

zjysteven/PrivacyAttack_AT_FL

A privacy attack that exploits Adversarial Training models to compromise the privacy of Federated Learning systems.

Language: Python - Size: 3.09 MB - Last synced at: about 2 years ago - Pushed at: almost 3 years ago - Stars: 8 - Forks: 2

eth-sri/ACES

[SRML@ICLR 2022] Robust and Accurate -- Compositional Architectures for Randomized Smoothing

Language: Python - Size: 7.05 MB - Last synced at: about 1 year ago - Pushed at: over 3 years ago - Stars: 2 - Forks: 0

VITA-Group/Double-Win-LTH

[ICML 2022] "Data-Efficient Double-Win Lottery Tickets from Robust Pre-training" by Tianlong Chen, Zhenyu Zhang, Sijia Liu, Yang Zhang, Shiyu Chang, Zhangyang Wang

Language: Python - Size: 308 KB - Last synced at: 2 months ago - Pushed at: about 3 years ago - Stars: 9 - Forks: 0

imrahulr/adversarial_robustness_pytorch

Unofficial implementation of the DeepMind papers "Uncovering the Limits of Adversarial Training against Norm-Bounded Adversarial Examples" & "Fixing Data Augmentation to Improve Adversarial Robustness" in PyTorch

Language: Python - Size: 54.7 KB - Last synced at: over 2 years ago - Pushed at: over 3 years ago - Stars: 66 - Forks: 8

yangarbiter/nearest-category-generalization

Nearest Category Generalization

Language: Jupyter Notebook - Size: 4.6 MB - Last synced at: almost 2 years ago - Pushed at: over 2 years ago - Stars: 0 - Forks: 0

emaballarin/RADLER 📦

[Partial] RADLER: (adversarially) Robust Adversarial Distributional LEaRner

Language: Python - Size: 225 KB - Last synced at: over 2 years ago - Pushed at: about 5 years ago - Stars: 2 - Forks: 0

yining043/Byzantine-Federeated-RL Fork of flint-xf-fan/Byzantine-Federeated-RL

This repo implements our paper, "Fault-Tolerant Federated Reinforcement Learning with Theoretical Guarantee", which has been accepted at NuerIPS 2021.

Language: Python - Size: 445 MB - Last synced at: over 2 years ago - Pushed at: over 2 years ago - Stars: 1 - Forks: 0

ALFA-group/CLAW-SAT Fork of OPTML-Group/CLAW-SAT

[SANER 2023] "CLAWSAT: Towards Both Robust and Accurate Code Models" by Jinghan Jia*, Shashank Srikant*, Tamara Mitrovska, Chuang Gan, Shiyu Chang, Sijia Liu, Una-May O'Reilly

Size: 27.6 MB - Last synced at: over 2 years ago - Pushed at: over 2 years ago - Stars: 0 - Forks: 0