{"id":13444326,"url":"https://github.com/yenchenlin/awesome-adversarial-machine-learning","last_synced_at":"2025-03-26T00:42:36.983Z","repository":{"id":45513399,"uuid":"76821215","full_name":"yenchenlin/awesome-adversarial-machine-learning","owner":"yenchenlin","description":"A curated list of awesome adversarial machine learning resources","archived":false,"fork":false,"pushed_at":"2020-11-26T16:09:26.000Z","size":27,"stargazers_count":1777,"open_issues_count":5,"forks_count":278,"subscribers_count":126,"default_branch":"master","last_synced_at":"2024-05-19T23:13:34.353Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":null,"has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/yenchenlin.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2016-12-19T02:30:11.000Z","updated_at":"2024-05-19T15:51:01.000Z","dependencies_parsed_at":"2022-07-18T08:13:13.067Z","dependency_job_id":null,"html_url":"https://github.com/yenchenlin/awesome-adversarial-machine-learning","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/yenchenlin%2Fawesome-adversarial-machine-learning","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/yenchenlin%2Fawesome-adversarial-machine-learning/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/yenchenlin%2Fawesome-adversarial-machine-learning/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/yenchenlin%2Fawesome-adversarial-machine-learning/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/yenchenlin","download_url":"https://codeload.github.com/yenchenlin/awesome-adversarial-machine-learning/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":245284715,"owners_count":20590307,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2024-07-31T04:00:19.853Z","updated_at":"2025-03-26T00:42:36.958Z","avatar_url":"https://github.com/yenchenlin.png","language":null,"funding_links":[],"categories":["Uncategorized","Awesome Lists","Others","9. Related Awesome Lists","Other useful repositories","Other Useful Repositories","Table of Contents","Other Lists","🛠️ Helpful Repositories","Awesome List","Programming/Comp Sci/SE Things","Outdated"],"sub_categories":["Uncategorized","6.2 LLM Jailbreak \u0026 Safety Benchmarks","TeX Lists","Ukraine","Q Learning","Explainability, Interpretability and Fairness"],"readme":"# :warning: Deprecated\nI no longer include up-to-date papers, but the list is still a good reference for starters.\n\n\n# Awesome Adversarial Machine Learning: [![Awesome](https://cdn.rawgit.com/sindresorhus/awesome/d7305f38d29fed78fa85652e3a63e154dd8e8829/media/badge.svg)](https://github.com/sindresorhus/awesome)\nA curated list of awesome adversarial machine learning resources, inspired by [awesome-computer-vision](https://github.com/jbhuang0604/awesome-computer-vision).\n\n## Table of Contents\n\n - [Blogs](#blogs)\n - [Papers](#papers)\n - [Talks](#talks)\n\n## Blogs\n * [Breaking Linear Classifiers on ImageNet](http://karpathy.github.io/2015/03/30/breaking-convnets/), A. Karpathy et al.\n * [Breaking things is easy](http://www.cleverhans.io/security/privacy/ml/2016/12/16/breaking-things-is-easy.html), N. Papernot \u0026 I. Goodfellow et al.\n * [Attacking Machine Learning with Adversarial Examples](https://blog.openai.com/adversarial-example-research/), N. Papernot, I. Goodfellow, S. Huang, Y. Duan, P. Abbeel, J. Clark.\n * [Robust Adversarial Examples](https://blog.openai.com/robust-adversarial-inputs/), Anish Athalye.\n * [A Brief Introduction to Adversarial Examples](http://people.csail.mit.edu/madry/lab/blog/adversarial/2018/07/06/adversarial_intro/), A. Madry et al.\n * [Training Robust Classifiers (Part 1)](http://people.csail.mit.edu/madry/lab/blog/adversarial/2018/07/11/robust_optimization_part1/), A. Madry et al.\n * [Adversarial Machine Learning Reading List](https://nicholas.carlini.com/writing/2018/adversarial-machine-learning-reading-list.html), N. Carlini\n * [Recommendations for Evaluating Adversarial Example Defenses](https://nicholas.carlini.com/writing/2018/evaluating-adversarial-example-defenses.html), N. Carlini\n\n \n## Papers\n### General\n * [Intriguing properties of neural networks](https://arxiv.org/abs/1312.6199), C. Szegedy et al., arxiv 2014\n * [Explaining and Harnessing Adversarial Examples](https://arxiv.org/abs/1412.6572), I. Goodfellow et al., ICLR 2015\n * [Motivating the Rules of the Game for Adversarial Example Research](https://arxiv.org/abs/1807.06732), J. Gilmer et al., arxiv 2018\n * [Wild Patterns: Ten Years After the Rise of Adversarial Machine Learning](https://arxiv.org/abs/1712.03141), B. Biggio, Pattern Recognition 2018\n\n### Attack\n**Image Classification**\n\n * [DeepFool: a simple and accurate method to fool deep neural networks](https://arxiv.org/abs/1511.04599), S. Moosavi-Dezfooli et al., CVPR 2016\n * [The Limitations of Deep Learning in Adversarial Settings](https://arxiv.org/abs/1511.07528), N. Papernot et al., ESSP 2016\n * [Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samples](https://arxiv.org/abs/1605.07277), N. Papernot et al., arxiv 2016\n * [Adversarial Examples In The Physical World](https://arxiv.org/pdf/1607.02533v3.pdf), A. Kurakin et al., ICLR workshop 2017 \n * [Delving into Transferable Adversarial Examples and Black-box Attacks](https://arxiv.org/abs/1611.02770) Liu et al., ICLR 2017\n * [Towards Evaluating the Robustness of Neural Networks](https://arxiv.org/abs/1608.04644) N. Carlini et al., SSP 2017\n * [Practical Black-Box Attacks against Deep Learning Systems using Adversarial Examples](https://arxiv.org/abs/1602.02697), N. Papernot et al., Asia CCS 2017\n * [Privacy and machine learning: two unexpected allies?](http://www.cleverhans.io/privacy/2018/04/29/privacy-and-machine-learning.html), I. Goodfellow et al.\n\n**Reinforcement Learning**\n\n* [Adversarial attacks on neural network policies](https://arxiv.org/abs/1702.02284), S. Huang et al, ICLR workshop 2017\n* [Tactics of Adversarial Attacks on Deep Reinforcement Learning Agents](https://arxiv.org/abs/1703.06748), Y. Lin et al, IJCAI 2017\n* [Delving into adversarial attacks on deep policies](https://arxiv.org/abs/1705.06452), J. Kos et al., ICLR workshop 2017\n\n**Segmentation \u0026 Object Detection**\n\n* [Adversarial Examples for Semantic Segmentation and Object Detection](https://arxiv.org/pdf/1703.08603.pdf), C. Xie, ICCV 2017\n\n**VAE-GAN**\n\n* [Adversarial examples for generative models](https://arxiv.org/abs/1702.06832), J. Kos et al. arxiv 2017\n\n**Speech Recognition**\n\n* [Audio Adversarial Examples: Targeted Attacks on Speech-to-Text](https://arxiv.org/abs/1801.01944), N. Carlini et al., arxiv 2018\n\n**Questiona Answering System**\n\n* [Adversarial Examples for Evaluating Reading Comprehension Systems](https://arxiv.org/abs/1707.07328), R. Jia et al., EMNLP 2017\n\n### Defence\n\n**Adversarial Training**\n\n* [Adversarial Machine Learning At Scale](https://arxiv.org/pdf/1611.01236.pdf), A. Kurakin et al., ICLR 2017\n* [Ensemble Adversarial Training: Attacks and Defenses](https://arxiv.org/abs/1705.07204), F. Tramèr et al., arxiv 2017\n\n**Defensive Distillation**\n* [Distillation as a Defense to Adversarial Perturbations against Deep Neural Networks](https://arxiv.org/pdf/1511.04508.pdf), N. Papernot et al., SSP 2016\n* [Extending Defensive Distillation](https://arxiv.org/abs/1705.05264), N. Papernot et al., arxiv 2017\n\n**Generative Model**\n* [PixelDefend: Leveraging Generative Models to Understand and Defend against Adversarial Examples](https://arxiv.org/abs/1710.10766), Y. Song et al., ICLR 2018\n* [Detecting Adversarial Attacks on Neural Network Policies with Visual Foresight](https://arxiv.org/abs/1710.00814), Y. Lin et al., NIPS workshop 2017\n\n### Regularization\n * [Distributional Smoothing with Virtual Adversarial Training](https://arxiv.org/abs/1507.00677), T. Miyato et al., ICLR 2016\n * [Adversarial Training Methods for Semi-Supervised Text Classification](https://arxiv.org/abs/1605.07725), T. Miyato et al., ICLR 2017\n\n### Others\n * [Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Images](https://arxiv.org/abs/1412.1897), A. Nguyen et al., CVPR 2015\n \n## Talks\n * [Do Statistical Models Understand the World?](https://www.youtube.com/watch?v=Pq4A2mPCB0Y), I. Goodfellow, 2015\n * [Classifiers under Attack](https://www.usenix.org/conference/enigma2017/conference-program/presentation/evans), David Evans, 2017\n  * [Adversarial Examples in Machine Learning](https://www.usenix.org/conference/enigma2017/conference-program/presentation/papernot), Nicolas Papernot, 2017\n  * [Poisoning Behavioral Malware Clustering](http://pralab.diee.unica.it/en/node/1121), Biggio. B, Rieck. K, Ariu. D, Wressnegger. C, Corona. I. Giacinto, G. Roli. F, 2014\n  * [Is Data Clustering in Adversarial Settings Secure?](http://pralab.diee.unica.it/en/node/955), BBiggio. B, Pillai. I, Rota Bulò. S, Ariu. D, Pelillo. M, Roli. F, 2015\n  * [Poisoning complete-linkage hierarchical clustering](http://pralab.diee.unica.it/en/node/1089), Biggio. B, Rota Bulò. S, Pillai. I, Mura. M, Zemene Mequanint. E, Pelillo. M, Roli. F, 2014\n  * [Is Feature Selection Secure against Training Data Poisoning?](https://pralab.diee.unica.it/en/node/1191), Xiao. H, Biggio. B, Brown. G, Fumera. G, Eckert. C, Roli. F, 2015\n  * [Adversarial Feature Selection Against Evasion Attacks](https://pralab.diee.unica.it/en/node/1188), \tZhang. F, Chan. PPK, Biggio. B, Yeung. DS, Roli. F, 2016\n\n## Licenses\nLicense\n\n[![CC0](http://i.creativecommons.org/p/zero/1.0/88x31.png)](http://creativecommons.org/publicdomain/zero/1.0/)\n\nTo the extent possible under law, [Yen-Chen Lin](http://yclin.me/) has waived all copyright and related or neighboring rights to this work.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fyenchenlin%2Fawesome-adversarial-machine-learning","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fyenchenlin%2Fawesome-adversarial-machine-learning","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fyenchenlin%2Fawesome-adversarial-machine-learning/lists"}