Adversarial Attack Frameworks

Tools and implementations for generating adversarial examples, attacking neural networks, and evaluating model robustness through adversarial perturbations. Does NOT include general model robustness, data poisoning, or non-adversarial security frameworks.

There are 66 adversarial attack frameworks tracked. 8 score above 50 (established tier). The highest-rated is Trusted-AI/adversarial-robustness-toolbox at 67/100 with 5,886 stars.

Get all 66 projects as JSON

curl "https://pt-edge.onrender.com/api/v1/datasets/quality?domain=ml-frameworks&subcategory=adversarial-attack-frameworks&limit=20"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.

#	Framework	Score	Tier	Stars	Language
1	Trusted-AI/adversarial-robustness-toolbox Adversarial Robustness Toolbox (ART) - Python Library for Machine Learning...	67	Established	5,886	Python
2	bethgelab/foolbox A Python toolbox to create adversarial examples that fool neural networks in...	64	Established	2,946	Python
3	DSE-MSU/DeepRobust A pytorch adversarial library for attack and defense methods on images and graphs	61	Established	1,080	Python
4	cleverhans-lab/cleverhans An adversarial example library for constructing attacks, building defenses,...	61	Established	6,425	Jupyter Notebook
5	BorealisAI/advertorch A Toolbox for Adversarial Robustness Research	58	Established	1,367	Jupyter Notebook
6	Hyperparticle/one-pixel-attack-keras Keras implementation of "One pixel attack for fooling deep neural networks"...	50	Established	1,232	Jupyter Notebook
7	Harry24k/adversarial-attacks-pytorch PyTorch implementation of adversarial attacks [torchattacks]	50	Established	2,147	Python
8	advboxes/AdvBox Advbox is a toolbox to generate adversarial examples that fool neural...	50	Established	1,412	Jupyter Notebook
9	cassidylaidlaw/perceptual-advex Code and data for the ICLR 2021 paper "Perceptual Adversarial Robustness:...	48	Emerging	56	Python
10	melihcatal/advsecurenet Machine Learning Security Library	47	Emerging	6	Python
11	Harry24k/PGD-pytorch A pytorch implementation of "Towards Deep Learning Models Resistant to...	47	Emerging	159	Jupyter Notebook
12	dipanjanS/adversarial-learning-robustness Contains materials for workshops pertaining to adversarial robustness in...	46	Emerging	86	Jupyter Notebook
13	EdisonLeeeee/Graph-Adversarial-Learning A curated collection of adversarial attack and defense on graph data.	46	Emerging	580	Python
14	hfawaz/ijcnn19attacks Adversarial Attacks on Deep Neural Networks for Time Series Classification	45	Emerging	80	Jupyter Notebook
15	airbnb/artificial-adversary 🗣️ Tool to generate adversarial text examples and test machine learning...	45	Emerging	402	Python
16	alexjfoote/reetoolbox Toolbox for measuring adversarial robustness to many transforms	45	Emerging	19	Jupyter Notebook
17	Harry24k/FGSM-pytorch A pytorch implementation of "Explaining and harnessing adversarial examples"	43	Emerging	70	Jupyter Notebook
18	microsoft/denoised-smoothing Provably defending pretrained classifiers including the Azure, Google, AWS,...	43	Emerging	102	Jupyter Notebook
19	jaxball/advis.js [Tensorflow.js] AdVis: Exploring real-time Adversarial Attacks in the...	42	Emerging	50	JavaScript
20	tao-bai/attack-and-defense-methods A curated list of papers on adversarial machine learning (adversarial...	42	Emerging	212	TeX
21	Adversarial-Deep-Learning/code-soup This is a collection of algorithms and approaches used in the book...	41	Emerging	17	Jupyter Notebook
22	GiorgosKarantonis/Adversarial-Attacks-with-Relativistic-AdvGAN Using relativism to improve GAN-based Adversarial Attacks. 🦾	41	Emerging	44	Python
23	safe-graph/graph-adversarial-learning-literature A curated list of adversarial attacks and defenses papers on graph-structured data.	41	Emerging	861	—
24	divelab/GOOD GOOD: A Graph Out-of-Distribution Benchmark [NeurIPS 2022 Datasets and Benchmarks]	40	Emerging	207	Python
25	syssec-utd/provninja Evading Provenance-Based ML Detectors with Adversarial System Actions	40	Emerging	35	Python
26	TortueSagace/versatile_evasion_attacks Security protocols for estimating adversarial robustness of machine learning...	40	Emerging	3	Jupyter Notebook
27	ChandlerBang/awesome-graph-attack-papers Adversarial attacks and defenses on Graph Neural Networks.	40	Emerging	391	—
28	chbrian/awesome-adversarial-examples-dl A curated list of awesome resources for adversarial examples in deep learning	40	Emerging	265	—
29	imrahulr/adversarial_robustness_pytorch Unofficial implementation of the DeepMind papers "Uncovering the Limits of...	39	Emerging	99	Python
30	sisinflab/adversarial-recommender-systems-survey The goal of this survey is two-fold: (i) to present recent advances on...	38	Emerging	164	—
31	ChandlerBang/Pro-GNN Implementation of the KDD 2020 paper "Graph Structure Learning for Robust...	38	Emerging	304	Python
32	um-dsp/Morphence Morphence: An implementation of a moving target defense against adversarial...	37	Emerging	23	Python
33	iamaaditya/pixel-deflection Deflecting Adversarial Attacks with Pixel Deflection	36	Emerging	72	Jupyter Notebook
34	THUMNLab/awesome-graph-ood Papers about out-of-distribution generalization on graphs.	36	Emerging	168	—
35	google-research/active-adversarial-tests Official implementation of the paper "Increasing Confidence in Adversarial...	36	Emerging	20	Python
36	prabhant/synthesizing-robust-adversarial-examples My entry for ICLR 2018 Reproducibility Challenge for paper Synthesizing...	35	Emerging	72	Jupyter Notebook
37	emaballarin/CARSO 👀🛡️ Code for the paper “Blending adversarial training and...	35	Emerging	8	Python
38	fiveai/GFCS Code for the ICLR 2022 paper "Attacking deep networks with surrogate-based...	34	Emerging	10	Python
39	lionelmessi6410/ntga Code for "Neural Tangent Generalization Attacks" (ICML 2021)	33	Emerging	41	Python
40	mikecamara/adversarial-machine-learning-attacks Adversarial Machine Learning Attacks in Scaled Self-Driving Cars is the...	32	Emerging	5	TeX
41	cuge1995/awesome-3D-point-cloud-attacks List of state of the art papers, code, and other resources	31	Emerging	111	—
42	Catminusminus/adv-examples-fun Try to generate adversarial images in your browser for fun and profit.	31	Emerging	4	TypeScript
43	cuge1995/Mesh-Attack our code for paper '3D Adversarial Attacks Beyond Point Cloud ', Information...	31	Emerging	36	Python
44	gralliry/Adversarial-Attack-Generation-Techniques Adversarial attack generation techniques for CIFAR10 based on Pytorch:...	30	Emerging	10	Python
45	nebula-beta/awesome-adversarial-deep-learning A list of awesome resources for adversarial attack and defense method in...	29	Experimental	132	—
46	ndb796/PyTorch-Adversarial-Attack-Baselines-for-ImageNet-CIFAR10-MNIST PyTorch adversarial attack baselines for ImageNet, CIFAR10, and MNIST...	29	Experimental	20	Jupyter Notebook
47	cudenver-ai/Adversarial-Machine-Learning Framework for the Adversarial Machine Learning Challenge at CU Denver,...	29	Experimental	9	JavaScript
48	serre-lab/Adversarial-Alignment Scaling-up deep neural networks to improve their performance on ImageNet...	29	Experimental	7	Jupyter Notebook
49	lancopku/well-classified-examples-are-underestimated Code for the AAAI 2022 publication "Well-classified Examples are...	29	Experimental	54	Jupyter Notebook
50	thupchnsky/sgc_unlearn Certified (approximate) machine unlearning for simplified graph...	27	Experimental	20	Python
51	Adversarial-Deep-Learning/adversarial-deep-learning.github.io Website for the book Adversarial Deep Learning	26	Experimental	8	HTML
52	AI-secure/adversarial-glue [NeurIPS 2021] "Adversarial GLUE: A Multi-Task Benchmark for Robustness...	24	Experimental	13	Python
53	VoDaiLocz/Lock-ART. Chống Al sao chép nghệ thuật của ảnh	21	Experimental	2	Python
54	AIRLABkhu/D-BADGE The official implementation of "D-BADGE: Decision-based Adversarial Batch...	20	Experimental	5	Jupyter Notebook
55	Adversarial-Deep-Learning/fencing Fencing is a playground for the algorithms and datasets discussed in the...	19	Experimental	3	—
56	TaoShuchang/G-NIA G-NIA model from "Single Node Injection Attack against Graph Neural...	19	Experimental	29	Python
57	ilias-ant/adversarial-validation A tiny framework to perform adversarial validation of your training and test data.	14	Experimental	24	Python
58	bad-antics/mirage Adversarial Machine Learning Toolkit - Model extraction, adversarial...	14	Experimental	1	Julia
59	hallucinaut/adversarial Detect and defend against adversarial attacks on ML models	13	Experimental	—	Go
60	neurodata/value-of-ood-data The value of out-of-distribution data (ICML 2023)	13	Experimental	10	Python
61	Ashly1991/adversarial-robustness-tf2 Adversarial example generation (FGSM/gradient sign) and adversarial training...	13	Experimental	—	Jupyter Notebook
62	deepmancer/adversarial-attacks-robustness Evaluating CNN robustness against various adversarial attacks, including...	12	Experimental	5	Jupyter Notebook
63	harry-kav/LittleAdversary LittleAdversary is an adversarial machine learning library made to aid...	12	Experimental	1	Jupyter Notebook
64	jaypmorgan/adaptive-neighbourhoods Python API for generating adapted and unique neighbourhoods for searching...	11	Experimental	—	C++
65	Trustworthy-ML-Lab/effective_skill_unlearning [NAACL 25] Two novel, light-weight, and training-free skill unlearning...	11	Experimental	4	Python
66	aaaastark/adversarial-network-attack-noise-on-mnist-dataset-pytorch Adversarial Network Attacks (PGD, pixel, FGSM) Noise on MNIST Images Dataset...	10	Experimental	2	—

Comparisons in this category

foolbox and AdvBox (64 vs 50) adversarial-attacks-pytorch and PGD-pytorch (50 vs 47)