adversarial-attacks

There are 47 repositories under adversarial-attacks topic.

BishopFox / sliver
Adversary Emulation Framework
security-tools implant golang dns-server http c2 command-and-control red-team red-teaming red-team-engagement adversarial-attacks adversary-simulation sliver gplv3 dns
Language:Go 7660
Trusted-AI / adversarial-robustness-toolbox
Adversarial Robustness Toolbox (ART) - Python Library for Machine Learning Security - Evasion, Poisoning, Extraction, Inference - Red and Blue Teams
python attack adversarial-machine-learning poisoning trusted-ai artificial-intelligence extraction adversarial-attacks adversarial-examples evasion inference privacy ai trustworthy-ai red-team blue-team machine-learning
Language:Python 4502
makcedward / nlpaug
Data augmentation for NLP
nlp augmentation machine-learning artificial-intelligence data-science natural-language-processing adversarial-attacks adversarial-example ai ml
Language:Jupyter Notebook 4317
QData / TextAttack
TextAttack 🐙 is a Python framework for adversarial attacks, data augmentation, and model training in NLP https://textattack.readthedocs.io/en/master/
machine-learning security natural-language-processing nlp adversarial-machine-learning adversarial-attacks data-augmentation adversarial-examples
Language:Python 2773
bethgelab / foolbox
A Python toolbox to create adversarial examples that fool neural networks in PyTorch, TensorFlow, and JAX
adversarial-examples machine-learning python adversarial-attacks pytorch tensorflow jax keras
Language:Python 2664
microsoft / promptbench
A unified evaluation framework for large language models
adversarial-attacks chatgpt evaluation large-language-models robustness prompt prompt-engineering benchmark
Language:Python 2106
Harry24k / adversarial-attacks-pytorch
PyTorch implementation of adversarial attacks [torchattacks].
deep-learning pytorch adversarial-attacks
Language:Python 1742
thunlp / TAADpapers
Must-read Papers on Textual Adversarial Attack and Defense
paper-list nlp adversarial-learning adversarial-attacks adversarial-defense natural-language-processing
Language:Python 1459
AdvBox
advboxes / AdvBox
Advbox is a toolbox to generate adversarial examples that fool neural networks in PaddlePaddle、PyTorch、Caffe2、MxNet、Keras、TensorFlow and Advbox can benchmark the robustness of machine learning models. Advbox give a command line tool to generate adversarial examples with Zero-Coding.
adversarial-examples paddlepaddle machine-learning security deep-learning adversarial-example onnx graphpipe fgsm adversarial-attacks deepfool
Language:Jupyter Notebook 1368
BorealisAI / advertorch
A Toolbox for Adversarial Robustness Research
pytorch adversarial-examples adversarial-example adversarial-perturbations adversarial-attacks adversarial-machine-learning adversarial-learning robustness toolbox security machine-learning benchmarking
Language:Jupyter Notebook 1275
DSE-MSU / DeepRobust
A pytorch adversarial library for attack and defense methods on images and graphs
adversarial-attacks adversarial-examples deep-neural-networks defense graph-neural-networks machine-learning deep-learning graph-convolutional-networks graph-mining
Language:Python 946
shubhomoydas / ad_examples
A collection of anomaly detection methods (iid/point-based, graph and time series) including active learning for anomaly detection/discovery, bayesian rule-mining, description for diversity/explanation/interpretability. Analysis of incorporating label feedback with ensemble and tree-based detectors. Includes adversarial attacks with Graph Convolutional Network.
ensemble-learning active-learning anomaly-detection rnn lstm explaination interpretability time-series timeseries trees unsuperivsed autoencoder streaming concept-drift generative-adversarial-network gan anogan graph-convolutional-networks adversarial-attacks nettack
Language:Python 834
safe-graph / graph-adversarial-learning-literature
A curated list of adversarial attacks and defenses papers on graph-structured data.
machine-learning graph-algorithms adversarial-machine-learning data-mining awesome-list literature-review deep-learning security graph-attack adversarial-attacks survey graph-data
810
thunlp / OpenAttack
An Open-Source Package for Textual Adversarial Attack.
adversarial-attacks nlp adversarial-example natural-language-processing pytorch
Language:Python 652
fra31 / auto-attack
Code relative to "Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks"
adversarial-defenses adversarial-attacks adversarial-robustness
Language:Python 611
hendrycks / natural-adv-examples
A Harder ImageNet Test Set (CVPR 2021)
adversarial-attacks robustness adversarial-example ml-safety imagenet domain-generalization
Language:Python 574
MadryLab / photoguard
Raising the Cost of Malicious AI-Powered Image Editing
adversarial-attacks adversarial-examples deep-learning deepfakes robustness stable-diffusion computer-vision
Language:Jupyter Notebook 532
jind11 / TextFooler
A Model for Natural Language Attack on Text Classification and Inference
adversarial-attacks bert bert-model natural-language-inference natural-language-processing text-classification
Language:Python 475
thu-ml / ares
A Python library for adversarial machine learning focusing on benchmarking adversarial robustness.
adversarial-machine-learning benchmark-framework adversarial-attacks adversarial-robustness fgsm bim mi-fgsm deepfool nes spsa boundary evolutionary mmlda distillation hgd pca
Language:Python 460
ThuCCSLab / Awesome-LM-SSP
A reading list for large models safety, security, and privacy.
adversarial-attacks awesome-list diffusion-models jailbreak language-model llm nlp privacy safety security vlm
426
sarathknv / adversarial-examples-pytorch
Implementation of Papers on Adversarial Examples
adversarial-attacks adversarial-defence adversarial-examples adversarial-images adversarial-learning adversarial-networks adversarial-perturbations deep-learning deep-neural-networks fgsm generative-adversarial-networks opencv perturbations python3 pytorch random-perturbations semantic-adversarial-examples visualization
Language:Python 376
ChandlerBang / awesome-graph-attack-papers
Adversarial attacks and defenses on Graph Neural Networks.
adversarial-attacks graph-neural-networks literature-review machine-learning deep-learning defense graph robustness adversarial-examples awesome awesome-list
346
AIJack
Koukyosyumei / AIJack
Security and Privacy Risk Simulator for Machine Learning (arXiv:2312.17667)
security machine-learning adversarial-attacks adversarial-examples adversarial-machine-learning membership-inference model-inversion-attacks evasion-attack poisoning-attacks privacy deep-learning homomorphic-encryption differential-privacy paillier paillier-cryptosystem federated-learning k-anonymity dbms
Language:C++ 331
natanielruiz / disrupting-deepfakes
🔥🔥Defending Against Deepfakes Using Adversarial Attacks on Conditional Image Translation Networks
adversarial-attacks disrupting-deepfakes deepfakes deep-learning machine-learning computer-vision deepfake-detection face-swap faceswap fake-news defending defending-deepfakes
Language:Python 298
adversarial-explainable-ai
hbaniecki / adversarial-explainable-ai
💡 Adversarial attacks on explanations and how to defend them
interpretable-machine-learning adversarial-machine-learning iml adversarial-attacks interpretability xai explainable-ai adversarial-examples explainability attacks security responsible-ai robustness interpretable adversarial model evaluation deep counterfactual defense
281
agencyenterprise / PromptInject
PromptInject is a framework that assembles prompts in a modular fashion to provide a quantitative analysis of the robustness of LLMs to adversarial prompt attacks. 🏆 Best Paper Awards @ NeurIPS ML Safety Workshop 2022
ai-safety language-models ml-safety agi ai-alignment agi-alignment adversarial-attacks gpt-3 large-language-models machine-learning chain-of-thought prompt-engineering
Language:Python 275
ChandlerBang / Pro-GNN
Implementation of the KDD 2020 paper "Graph Structure Learning for Robust Graph Neural Networks"
graph-neural-networks adversarial-attacks defense deep-learning machine-learning graph-structure-recovery graph-mining attack-defense semi-supervised-learning pytorch
Language:Python 273
ain-soph / trojanzoo
TrojanZoo provides a universal pytorch platform to conduct security researches (especially backdoor attacks/defenses) of image classification in deep learning.
pytorch backdoor-attacks image-classification adversarial-attacks deep-learning
Language:Python 268
HuntDownProject / HEDnsExtractor
A suite for hunting suspicious targets, expose domains and phishing discovery
threat-hunting threat-intelligence threatintel adversarial-attacks malware-analysis phishing-detection
Language:Go 268
1Konny / FGSM
Simple pytorch implementation of FGSM and I-FGSM
adversarial-example adversarial-attacks machine-learning-security
Language:Python 265
deadbits / vigil-llm
⚡ Vigil ⚡ Detect prompt injections, jailbreaks, and other potentially risky Large Language Model (LLM) inputs
llm-security prompt-injection adversarial-attacks adversarial-machine-learning large-language-models llmops yara-scanner security-tools
Language:Python 247
automorphic-ai / aegis
Self-hardening firewall for large language models
adversarial-attacks large-language-models llmops prompt-injection security
Language:Python 243
kabkabm / defensegan
Defense-GAN: Protecting Classifiers Against Adversarial Attacks Using Generative Models (published in ICLR2018)
deep-learning adversarial-attacks adversarial-examples iclr2018 generative-adversarial-network
Language:Python 224
danielzuegner / nettack
Implementation of the paper "Adversarial Attacks on Neural Networks for Graph Data".
machine-learning adversarial-attacks graph-mining deep-learning neural-networks
Language:Python 217
haofanwang / Awesome-Computer-Vision
Awesome Resources for Advanced Computer Vision Topics
3d-vision adversarial-attacks automl awesome-list computer-vision deep-learning denoising gan graph-neural-network interpretability object-detection paper pose-estimation super-resolution trajectory-prediction transfer-learning video-analysis vision-and-language vision-project
210
ryderling / DEEPSEC
DEEPSEC: A Uniform Platform for Security Analysis of Deep Learning Model
adversarial-attacks adversarial-examples defenses deep-leaning
Language:Python 206