[深度学习论文笔记][Adversarial Examples] Explaining and Harnessing Adversarial Examples
来源:互联网 发布:中国大数据时代 编辑:程序博客网 时间:2024/05/20 07:18
Goodfellow, Ian J., Jonathon Shlens, and Christian Szegedy. “Explaining and harnessing adversarial examples.” arXiv preprint arXiv:1412.6572 (2014). (Citations: 129).
10.3.1 Fast Gradient Sign Method
Suppose we want to permutate X a little bit as X + ε, We can make many infinitesimal changes to the input that add up to one large change to the output.
Goal
Linearize the cost function
See Fig.
2 Analysis
CNNs work well on naturally occuring data, but is exposed as a fake when one visits points in space that do not have high probability in the data distribution.
Adversarial examples can be explained as a property of high-dimensional dot products. They are a result of models being too linear, rather than too nonlinear. Generic regularization strategies such as dropout, pretraining, and model averaging do not confer a significant reduction in a model’s vulnerability to adversarial examples, but changing to nonlinear model families such as RBF networks can do so.
The generalization of adversarial examples across different models can be explained as a result of adversarial perturbations being highly aligned with the weight vectors of a model, and different models learning similar functions when trained to perform the same task.
By training on a mixture of adversarial and clean examples, a neural network could be regularized somewhat.
In particular, this is not a problem with Deep Learning, and has little to do with ConvNets specifically. Same issue would come up with Neural Nets in any other modalities.
- [深度学习论文笔记][Adversarial Examples] Explaining and Harnessing Adversarial Examples
- CS231n学习笔记--16. Adversarial Examples and Adversarial Training
- [深度学习论文笔记][Adversarial Examples] Intriguing properties of neural networks
- [深度学习论文笔记][Adversarial Examples] Deep Neural Networks are Easily Fooled: High Confidence Predictions
- 生成对抗网络 - Adversarial Examples 对抗样本
- [深度学习论文笔记][ICCV 17]Semi Supervised Semantic Segmentation Using Generative Adversarial Net
- Generative adversarial nets 论文笔记
- 生成对抗网络学习笔记1----论文Generative Adversarial Nets
- 深度学习(四十六)Adversarial Autoencoders学习笔记
- Generative Adversarial Nets论文笔记+代码解析
- Conditional Generative Adversarial Nets论文笔记
- [semantic segmentation] using Adversarial Networks 论文学习
- 深度学习(7):Generative Adversarial Networks
- 《DeLiGAN : Generative Adversarial Networks for Diverse and Limited Data》论文笔记
- 生成对抗网络学习笔记3----论文unsupervised representation learning with deep convolutional generative adversarial
- 深度学习笔记一:生成对抗网络(Generative Adversarial Nets)
- 《zi2zi: Master Chinese Calligraphy with Conditional Adversarial Networks》论文笔记
- 《Image-to-Image Translation with Conditional Adversarial Networks》论文笔记
- vs2013的快捷键
- Linux下Tomcat的安装配置
- 412. Fizz Buzz
- YDB的安装部署
- 性能优化的常见模式及趋势|小丘
- [深度学习论文笔记][Adversarial Examples] Explaining and Harnessing Adversarial Examples
- 关于FD_WRITE何时触发
- 关于 supermap 发布跟踪图层后 生成的缓存模型不更变问题
- 进度
- 苹果根证书异常删除导致 App 闪退的问题
- android studio从入门到提高到精通详解。。。
- springBoot项目代码加密总结
- Sign In and Sign Out
- CNN系列