只是一个自己看过的论文小汇总，还不能当综述，但也包含了很多经典的对抗攻击算法，方便回顾和查询，自己看的第一篇综述是：
Advances in adversarial attacks and defenses in computer vision: A survey
论文这件事，真的只能多看，上学期看的，现在忘差不多了（估计还得从头再看亿遍），代码也得操练起来。
由于我没给论文链接（比较费时间），我就介绍几个搜索文献的网站
代码就看论文中有没有给链接吧，然后就 paperswitchcode，基本上每一篇都有。后面有时间会编辑个论文和代码链接吧，然后简单介绍每种算法的idea和method，比较经典的应该会单出论文笔记。
算法的分类没有那么严格，可能会有一些出入，新看的论文会再加入，持续更新。
术语含义white-box attack白盒攻击：知道模型的全部信息black-box attack黑盒攻击：无法获知模型的训练过程和参数query-based attack基于查询的攻击：攻击者能够查询目标模型并利用其输出来优化对抗性图像score-based attack基于分数的攻击：需要知道模型的输出的置信度decision-based attack基于决策的攻击：只需要知道目标模型的预测标签（top-1 label）targeted attacks定向攻击，欺骗模型使模型预测为特定标签；相对于un-targeted attacks，没有特定标签，只求模型预测错误adversarial training对抗训练：在模型的训练数据中注入对抗性例子以使其具有对抗鲁棒性
首先：对抗攻击的最先提出：Intriguing properties of neural networks
1.FGSM
（1） FGSM：EXPLAINING AND HARNESSING ADVERSARIAL EXAMPLES
（2） I-FGSM：ADVERSARIAL EXAMPLES IN THE PHYSICAL WORLD
（3） MI-FGSM：Boosting Adversarial Attacks with Momentum（白盒黑盒均适用）
（4） NI-FGSM,SIM：NESTEROV ACCELERATED GRADIENT AND SCALE INVARIANCE FOR ADVERSARIAL ATTACKS（增加迁移性）
2.JSMA：
The Limitations of Deep Learning in Adversarial Settings
3.DeepFool：
DeepFool: a simple and accurate method to fool deep neural networks
4.CW：
Towards Evaluating the Robustness of Neural Networks
5.PGD:
Towards Deep Learning Models Resistant to Adversarial Attacks
黑盒开篇：Practical Black-Box Attacks against Machine Learning
1.单像素攻击
（1）Simple Black-Box Adversarial Attacks on Deep Neural Networks
（2）One Pixel Attack for Fooling Deep Neural Networks
2.基于查询（query-based attack）
基于查询的又可分为基于分数的和基于决策的
socre-based attack
（1） ZOO——ZOO: Zeroth Order Optimization Based Black-box Attacks to
Deep Neural Networks without Training Substitute Models
（2） AutoZOO——AutoZOOM: Autoencoder-Based Zeroth Order Optimization Method for Attacking Black-Box Neural Networks
（3） QL——Black-box Adversarial Attacks with Limited Queries and
Information
(4) N Attack——N ATTACK: Learning the Distributions of Adversarial Examples for an Improved Black-Box Attack on Deep Neural Networks
（5） SimBA——Simple Black-box Adversarial Attacks
（6） MetaSimulator——Simulating Unknown Target Models for Query-Efficient Black-box Attacks
decision-based attack
（1） 开篇 Boundary Attack——Decision-Based Adversarial Attacks: Reliable Attacks Against Black-Box Machine learning Models
（2） HSJA——HopSkipJumpAttack: A Query-Efficient Decision-Based Attack
（3） SurFree——SurFree: a fast surrogate-free black-box attack
（4） f-attack——Decision-Based Adversarial Attack With Frequency Mixup
（5） TREMBA——BLACK-BOX ADVERSARIAL ATTACK WITH TRANSFERABLE MODEL-BASED EMBEDDING
3.基于迁移
（1） 开篇：Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samples
（2）Delving into Transferable Adversarial Examples and Black-box Attacks
（3）Enhancing the Transferability of Adversarial Attacks through Variance Tuning
（3）元学习：Meta Gradient Adversarial Attack
4.基于替代
（1）DaST:Data-free Substitute Training for Adversarial Attacks
（2）Delving into Data: Effectively Substitute Training for Black-box Attack
（3）Learning Transferable Adversarial Examples via Ghost Networks
5.其他
（1）通用黑盒攻击UAP：Universal adversarial perturbations
（2）AdvDrop: Adversarial Attack to DNNs by Dropping Information
（3）Practical No-box Adversarial Attacks against DNNs
（4）ZOO: Zeroth Order Optimization Based Black-box Attacks to Deep Neural Networks without Training Substitute Models
Original: https://blog.csdn.net/ji_meng/article/details/124063863
Author: nanyidev
Title: 对抗攻击算法总结论文集合（白盒、黑盒、目标检测、对抗训练等）
原创文章受到原创版权保护。转载请注明出处：https://www.johngo689.com/648539/
转载文章受原作者版权保护。转载请注明原作者出处！