An open API service indexing awesome lists of open source software.

Adversarial attacks

Adversarial attacks are techniques that craft intentionally perturbed inputs to mislead machine learning models into producing incorrect outputs. They are central to research in AI robustness, security, and trustworthiness.

https://github.com/trusted-ai/adversarial-robustness-toolbox

Adversarial Robustness Toolbox (ART) - Python Library for Machine Learning Security - Evasion, Poisoning, Extraction, Inference - Red and Blue Teams

adversarial-attacks adversarial-examples adversarial-machine-learning ai artificial-intelligence attack blue-team evasion extraction inference machine-learning poisoning privacy python red-team trusted-ai trustworthy-ai

Last synced: 13 May 2025

https://github.com/Trusted-AI/adversarial-robustness-toolbox

Adversarial Robustness Toolbox (ART) - Python Library for Machine Learning Security - Evasion, Poisoning, Extraction, Inference - Red and Blue Teams

adversarial-attacks adversarial-examples adversarial-machine-learning ai artificial-intelligence attack blue-team evasion extraction inference machine-learning poisoning privacy python red-team trusted-ai trustworthy-ai

Last synced: 23 Mar 2025

https://github.com/QData/TextAttack

TextAttack 🐙 is a Python framework for adversarial attacks, data augmentation, and model training in NLP https://textattack.readthedocs.io/en/master/

adversarial-attacks adversarial-examples adversarial-machine-learning data-augmentation machine-learning natural-language-processing nlp security

Last synced: 02 Apr 2025

https://github.com/qdata/textattack

TextAttack 🐙 is a Python framework for adversarial attacks, data augmentation, and model training in NLP https://textattack.readthedocs.io/en/master/

adversarial-attacks adversarial-examples adversarial-machine-learning data-augmentation machine-learning natural-language-processing nlp security

Last synced: 17 Apr 2026

https://github.com/bethgelab/foolbox

A Python toolbox to create adversarial examples that fool neural networks in PyTorch, TensorFlow, and JAX

adversarial-attacks adversarial-examples jax keras machine-learning python pytorch tensorflow

Last synced: 14 May 2025

https://github.com/harry24k/adversarial-attacks-pytorch

PyTorch implementation of adversarial attacks [torchattacks]

adversarial-attacks deep-learning pytorch

Last synced: 11 Apr 2025

https://github.com/Harry24k/adversarial-attacks-pytorch

PyTorch implementation of adversarial attacks [torchattacks]

adversarial-attacks deep-learning pytorch

Last synced: 27 Mar 2025

https://github.com/CryptoAILab/Awesome-LM-SSP

A reading list for large models safety, security, and privacy (including Awesome LLM Security, Safety, etc.).

adversarial-attacks awesome-list diffusion-models jailbreak language-model llm nlp privacy safety security vlm

Last synced: 18 Jan 2026

https://github.com/thunlp/taadpapers

Must-read Papers on Textual Adversarial Attack and Defense

adversarial-attacks adversarial-defense adversarial-learning natural-language-processing nlp paper-list

Last synced: 14 May 2025

https://github.com/thunlp/TAADpapers

Must-read Papers on Textual Adversarial Attack and Defense

adversarial-attacks adversarial-defense adversarial-learning natural-language-processing nlp paper-list

Last synced: 27 Mar 2025

https://github.com/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-attacks adversarial-example adversarial-examples deep-learning deepfool fgsm graphpipe machine-learning onnx paddlepaddle security

Last synced: 08 Apr 2025

https://github.com/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-attacks adversarial-example adversarial-examples deep-learning deepfool fgsm graphpipe machine-learning onnx paddlepaddle security

Last synced: 15 Mar 2025

https://github.com/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.

active-learning adversarial-attacks anogan anomaly-detection autoencoder concept-drift ensemble-learning explaination gan generative-adversarial-network graph-convolutional-networks interpretability lstm nettack rnn streaming time-series timeseries trees unsuperivsed

Last synced: 16 Mar 2025

https://github.com/thunlp/openattack

An Open-Source Package for Textual Adversarial Attack.

adversarial-attacks adversarial-example natural-language-processing nlp pytorch

Last synced: 08 Apr 2025

https://github.com/thunlp/OpenAttack

An Open-Source Package for Textual Adversarial Attack.

adversarial-attacks adversarial-example natural-language-processing nlp pytorch

Last synced: 30 Mar 2025

https://github.com/fra31/auto-attack

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

adversarial-attacks adversarial-defenses adversarial-robustness

Last synced: 18 Jan 2026

https://github.com/thu-ml/ares

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

adversarial-attacks adversarial-machine-learning adversarial-robustness benchmark-framework bim boundary deepfool distillation evolutionary fgsm hgd mi-fgsm mmlda nes pca spsa

Last synced: 04 Apr 2025

https://github.com/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

Last synced: 18 Apr 2025

https://github.com/deadbits/vigil-llm

⚡ Vigil ⚡ Detect prompt injections, jailbreaks, and other potentially risky Large Language Model (LLM) inputs

adversarial-attacks adversarial-machine-learning large-language-models llm-security llmops prompt-injection security-tools yara-scanner

Last synced: 06 Apr 2025

https://github.com/HuntDownProject/HEDnsExtractor

A suite for hunting suspicious targets, expose domains and phishing discovery

adversarial-attacks malware-analysis phishing-detection threat-hunting threat-intelligence threatintel

Last synced: 05 Aug 2025

https://github.com/ChandlerBang/Pro-GNN

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

adversarial-attacks attack-defense deep-learning defense graph-mining graph-neural-networks graph-structure-recovery machine-learning pytorch semi-supervised-learning

Last synced: 21 Jul 2025

https://github.com/wuyoscar/ISC-Bench

ISC-Bench: Internal Safety Collapse in Frontier LLMs | JailbreakArena | 56 TVD templates | AI Safety Benchmark | Agent Safety | Red Teaming | Jailbreak

adversarial-attacks agent-safety ai-safety benchmark frontier-models jailbreak large-language-models llm-safety red-teaming safety-evaluation

Last synced: 02 Apr 2026

https://github.com/chandlerbang/pro-gnn

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

adversarial-attacks attack-defense deep-learning defense graph-mining graph-neural-networks graph-structure-recovery machine-learning pytorch semi-supervised-learning

Last synced: 09 Apr 2025

https://github.com/ain-soph/trojanzoo

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

adversarial-attacks backdoor-attacks deep-learning image-classification pytorch

Last synced: 25 Dec 2025

https://github.com/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

adversarial-attacks agi agi-alignment ai-alignment ai-safety chain-of-thought gpt-3 language-models large-language-models machine-learning ml-safety prompt-engineering

Last synced: 05 Apr 2025

https://github.com/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

adversarial-attacks agi agi-alignment ai-alignment ai-safety chain-of-thought gpt-3 language-models large-language-models machine-learning ml-safety prompt-engineering

Last synced: 28 Mar 2025

https://github.com/natanielruiz/disrupting-deepfakes

🔥🔥Defending Against Deepfakes Using Adversarial Attacks on Conditional Image Translation Networks

adversarial-attacks computer-vision deep-learning deepfake-detection deepfakes defending defending-deepfakes disrupting-deepfakes face-swap faceswap fake-news machine-learning

Last synced: 04 Nov 2025

https://github.com/automorphic-ai/aegis

Self-hardening firewall for large language models

adversarial-attacks large-language-models llmops prompt-injection security

Last synced: 28 Mar 2025

https://github.com/VinAIResearch/Anti-DreamBooth

Anti-DreamBooth: Protecting users from personalized text-to-image synthesis (ICCV 2023)

adversarial-attacks dreambooth personalization stable-diffusion text-to-image

Last synced: 27 Mar 2025

https://github.com/ryderling/DEEPSEC

DEEPSEC: A Uniform Platform for Security Analysis of Deep Learning Model

adversarial-attacks adversarial-examples deep-leaning defenses

Last synced: 20 Apr 2025

https://github.com/bosch-aisecurity-aishield/watchtower

AIShield Watchtower: Dive Deep into AI's Secrets! 🔍 Open-source tool by AIShield for AI model insights & vulnerability scans. Secure your AI supply chain today! ⚙️🛡️

adversarial-attacks aisec keras mlops mlsecops pytorch safetensors scikit-learn security security-automation security-tools supply-chain tensorflow vulnerability-scanners

Last synced: 18 Apr 2025

https://github.com/Harry24k/PGD-pytorch

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

adversarial-attacks deep-learning pytorch

Last synced: 20 Feb 2026

https://github.com/harry24k/pgd-pytorch

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

adversarial-attacks deep-learning pytorch

Last synced: 07 Sep 2025

https://github.com/gmh14/RobNets

[CVPR 2020] When NAS Meets Robustness: In Search of Robust Architectures against Adversarial Attacks

adversarial-attacks adversarial-examples deep-learning-architectures neural-architecture-search robustness

Last synced: 12 May 2025

https://github.com/git-disl/TOG

Real-time object detection is one of the key applications of deep neural networks (DNNs) for real-world mission-critical systems. While DNN-powered object detection systems celebrate many life-enriching opportunities, they also open doors for misuse and abuse. This project presents a suite of adversarial objectness gradient attacks, coined as TOG, which can cause the state-of-the-art deep object detection networks to suffer from untargeted random attacks or even targeted attacks with three types of specificity: (1) object-vanishing, (2) object-fabrication, and (3) object-mislabeling. Apart from tailoring an adversarial perturbation for each input image, we further demonstrate TOG as a universal attack, which trains a single adversarial perturbation that can be generalized to effectively craft an unseen input with a negligible attack time cost. Also, we apply TOG as an adversarial patch attack, a form of physical attacks, showing its ability to optimize a visually confined patch filled with malicious patterns, deceiving well-trained object detectors to misbehave purposefully.

adversarial-attacks faster-rcnn object-detection ssd yolov3

Last synced: 21 Apr 2025

https://github.com/vita-epfl/s-attack

[CVPR 2025] Official implementation of three papers "Certified Human Trajectory Prediction", "Vehicle trajectory prediction works, but not everywhere", and "Are socially-aware trajectory prediction models really socially-aware?".

adversarial-attacks deep-learning human-behavior-understanding human-trajectory-prediction robustness vehicle-trajectory-prediction

Last synced: 16 Jan 2026

https://github.com/safellama/plexiglass

A toolkit for detecting and protecting against vulnerabilities in Large Language Models (LLMs).

adversarial-attacks adversarial-machine-learning cybersecurity deep-learning deep-neural-networks machine-learning security

Last synced: 18 Apr 2025

https://github.com/thudm/grb

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

adversarial-attacks deep-learning graph-neural-networks machine-learning pytorch

Last synced: 24 Jul 2025

https://github.com/Eaphan/Robust3DOD

A Comprehensive Study of the Robustness for LiDAR-based 3D Object Detectors against Adversarial Attacks

3d-object-detection adversarial-attacks

Last synced: 20 Mar 2025

https://github.com/shawnxyang/face-robustness-benchmark

An adversarial robustness evaluation library on face recognition.

adversarial-attacks face-recognition machine-learning robustness

Last synced: 04 Jul 2025

https://github.com/dipanjans/adversarial-learning-robustness

Contains materials for workshops pertaining to adversarial robustness in deep learning.

adversarial-attacks adversarial-learning computer-vision deep-learning python tensorflow

Last synced: 30 Apr 2025

https://github.com/thunlp/sememepso-attack

Code and data of the ACL 2020 paper "Word-level Textual Adversarial Attacking as Combinatorial Optimization"

adversarial-attacks adversarial-examples nlp pso sememe

Last synced: 25 Apr 2025

https://github.com/392781/faceoff

Steps towards physical adversarial attacks on facial recognition

adversarial-attacks adversarial-machine-learning facenet-pytorch facial-recognition physical-adversarial-attacks

Last synced: 17 Mar 2025

https://github.com/hfawaz/ijcnn19attacks

Adversarial Attacks on Deep Neural Networks for Time Series Classification

adversarial-attacks adversarial-examples deep-learning deep-neural-networks time-series-classification

Last synced: 09 Apr 2025

https://github.com/osu-nlp-group/amplegcg

AmpleGCG: Learning a Universal and Transferable Generator of Adversarial Attacks on Both Open and Closed LLM

adversarial-attacks gcg nlp safety

Last synced: 14 Oct 2025

https://github.com/dmitryryumin/wacv-2024-papers

WACV 2024 Papers: Discover cutting-edge research from WACV 2024, the leading computer vision conference. Stay updated on the latest in computer vision and deep learning, with code included. ⭐ support visual intelligence development!

3d-computer-vision 3d-sensor adversarial-attacks autonomous-driving biometrics computer-vision datasets face-recognition generative-models gesture-recognition image-recognition image-understanding low-level machine-learning robotics video-recognition vision-transformer visualization wacv wacv2024

Last synced: 12 Apr 2025

https://github.com/harry24k/fgsm-pytorch

A pytorch implementation of "Explaining and harnessing adversarial examples"

adversarial-attacks deep-learning pytorch

Last synced: 10 Apr 2025

https://github.com/Harry24k/FGSM-pytorch

A pytorch implementation of "Explaining and harnessing adversarial examples"

adversarial-attacks deep-learning pytorch

Last synced: 04 Mar 2026

https://github.com/ermongroup/generative_adversary

Code for the unrestricted adversarial examples paper (NeurIPS 2018)

adversarial-attacks adversarial-examples neurips2018

Last synced: 08 May 2025

https://github.com/bhheo/bss_distillation

Knowledge Distillation with Adversarial Samples Supporting Decision Boundary (AAAI 2019)

adversarial-attacks adversarial-samples image-classification knowledge-distillation network-compression teacher-student-learning

Last synced: 30 Apr 2025

https://github.com/pmichel31415/teapot-nlp

Tool for Evaluating Adversarial Perturbations on Text

adversarial-attacks natural-language-processing

Last synced: 22 Jul 2025

https://github.com/chandlerbang/simp-gcn

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

adversarial-attacks deep-learning graph-convolutional-networks graph-mining graph-neural-networks robustness

Last synced: 08 Apr 2025

https://github.com/anuragranj/flowattack

Attacking Optical Flow (ICCV 2019)

adversarial-attacks deep-learning optical-flow

Last synced: 05 Apr 2025

https://github.com/mims-harvard/GNNGuard

Defending graph neural networks against adversarial attacks (NeurIPS 2020)

adversarial-attacks deep-learning graph-convolutional-networks graph-neural-networks robust-learning

Last synced: 21 Jul 2025

https://github.com/yfzhang114/environment-label-smoothing

This is an official PyTorch implementation of the ICLR 2023 paper 《Free Lunch for Domain Adversarial Training: Environment Label Smoothing》.

adversarial-attacks deep-learning domain-adaptation machine-learning pytorch

Last synced: 07 Mar 2026

https://github.com/searchableai/kitanaqa

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

adversarial-attacks adversarial-training bert data-augmentation ml-automation natural-language-processing nlp pytorch question-answering transformer

Last synced: 10 Apr 2025

https://github.com/chandlerbang/gtrans

[ICLR'23] Implementation of "Empowering Graph Representation Learning with Test-Time Graph Transformation"

adversarial-attacks data-centric distribution-shift graph-neural-networks out-of-distribution robustness test-time-adaptation

Last synced: 08 Apr 2025

https://github.com/Harry24k/CW-pytorch

A pytorch implementation of "Towards Evaluating the Robustness of Neural Networks"

adversarial-attacks deep-learning pytorch

Last synced: 03 Apr 2025

https://github.com/harry24k/cw-pytorch

A pytorch implementation of "Towards Evaluating the Robustness of Neural Networks"

adversarial-attacks deep-learning pytorch

Last synced: 22 Aug 2025

https://github.com/UCSC-VLAA/vllm-safety-benchmark

[ECCV 2024] Official PyTorch Implementation of "How Many Unicorns Are in This Image? A Safety Evaluation Benchmark for Vision LLMs"

adversarial-attacks benchmark datasets llm multimodal-llm robustness safety vision-language-model

Last synced: 27 Jul 2025

https://github.com/spencerwooo/torchattack

🛡 A curated list of adversarial attacks in PyTorch, with a focus on transferable black-box attacks.

adversarial-attacks adversarial-examples pytorch

Last synced: 14 Apr 2025

https://github.com/dsgiitr/adversarial_lab

Web-based Tool for visualisation and generation of adversarial examples by attacking ImageNet Models like VGG, AlexNet, ResNet etc.

adversarial-attacks computer-vision flask html-css-javascript imagenet machine-learning python pytorch visualization

Last synced: 15 Apr 2025

https://github.com/max-andr/provably-robust-boosting

Provably Robust Boosted Decision Stumps and Trees against Adversarial Attacks [NeurIPS 2019]

adversarial-attacks boosted-decision-stumps boosted-trees boosting provable-defense

Last synced: 27 Mar 2025

https://github.com/SamSamhuns/yolov5_adversarial

Generate adversarial patches against YOLOv5 🚀

adversarial-attacks adversarial-machine-learning object-detection

Last synced: 21 Apr 2025

https://github.com/ajhamdi/advpc

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

3d adversarial-attacks deep-learning eccv-2020 paper point-clouds pointnet tensorflow

Last synced: 01 Aug 2025

https://github.com/ajhamdi/AdvPC

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

3d adversarial-attacks deep-learning eccv-2020 paper point-clouds pointnet tensorflow

Last synced: 20 Mar 2025

https://github.com/chawins/pal

PAL: Proxy-Guided Black-Box Attack on Large Language Models

adversarial-attacks jailbreak llm openai-api red-teaming

Last synced: 27 Jul 2025

https://github.com/daniel-liu-c0deb0t/adversarial-point-perturbations-on-3d-objects

New distributional and shape attacks on neural networks that process 3D point cloud data.

3d-point-clouds adversarial-attacks algorithms deep-learning matplotlib numba numpy pointnet python tensorflow

Last synced: 30 Oct 2025

https://github.com/Daniel-Liu-c0deb0t/Adversarial-point-perturbations-on-3D-objects

New distributional and shape attacks on neural networks that process 3D point cloud data.

3d-point-clouds adversarial-attacks algorithms deep-learning matplotlib numba numpy pointnet python tensorflow

Last synced: 20 Mar 2025

https://github.com/dvlab-research/lbgat

Learnable Boundary Guided Adversarial Training (ICCV2021)

adversarial-attacks adversarial-defense adversarial-training iccv2021 image-recognition robustness

Last synced: 13 Oct 2025

https://github.com/harry24k/mair

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

adversarial-attacks adversarial-defenses adversarial-robustness adversarial-training

Last synced: 10 Apr 2025