Generative adversarial models are powerful tools to model structure in complex distributions for a variety of tasks. Current techniques for learning generative models require an access to samples which have high quality, and advanced generative models are applied to generate samples from noisy training data through ambient modules. However, the modules are only practical for the output space of the generator, and their application in the hidden space is not well studied. In this paper, we extend the ambient module to the hidden space of the generator, and provide the uniqueness condition and the corresponding strategy for the ambient hidden generator in the adversarial training process. We report the practicality of the proposed method on the benchmark dataset.
Learning stochastic object models from medical imaging measurements by use of advanced ambient generative adversarial networks
University of California Santa Barbara(加州大学圣巴巴拉分校);Washington University in St. Louis(圣路易斯华盛顿大学);University of Illinois at Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校);Cancer Center at Illinois(伊利诺伊癌症中心)
Ambient Denoising Diffusion Generative Adversarial Networks for Establishing Stochastic Object Models from Noisy Image Data
Global Institute of Future Technology, Shanghai Jiao Tong University(上海交通大学未来技术研究院);University of Michigan-Shanghai Jiao Tong University Joint Institute, Shanghai Jiao Tong University(上海交通大学密歇根大学联合学院);University of Arizona(亚利桑那大学);Wyant College of Optical Sciences, University of Arizona(亚利桑那大学怀恩特光学科学学院)
Manifold Mixup: Better Representations by Interpolating Hidden States
Aalto Univeristy(阿尔托大学);Montréal Institute for Learning Algorithms(蒙特利尔学习算法研究所);Sharif University of Technology(谢里夫理工大学);Facebook AI Research(Facebook人工智能研究院)
Generative Adversarial Networks (GANs) have achieved a great success in unsupervised learning. Despite its remarkable empirical performance, there are limited theoretical studies on the statistical properties of GANs. This paper provides approximation and statistical guarantees of GANs for the estimation of data distributions that have densities in a Hölder space. Our main result shows that, if the generator and discriminator network architectures are properly chosen, GANs are consistent estimators of data distributions under strong discrepancy metrics, such as the Wasserstein-1 distance. Furt…
Microsoft Research(微软研究院);Carnegie Mellon University(卡内基梅隆大学)
Despite the empirical success of using Adversarial Training to defend deep learning models against adversarial perturbations, so far, it still remains rather unclear what the principles are behind the existence of adversarial perturbations, and what adversarial training does to the neural network to remove them. In this paper, we present a principle that we call Feature Purification, where we show one of the causes of the existence of adversarial examples is the accumulation of certain small dense mixtures in the hidden weights during the training process of a neural network; and more importan…
University of Toronto(多伦多大学);Google Brain(谷歌大脑);OpenAI
在本文中,我们提出了“对抗自动编码器”(AAE),这是一个概率自动编码器,它使用最近提出的生成对抗网络(GAN)进行变分推理匹配的聚合后验的隐藏代码向量的自动编码器与任意先验分布。将聚合后验与先验进行匹配可确保从先验空间的任何部分生成有意义的样本。因此,对抗性自动编码器的解码器学习一个深度生成模型,该模型将强加的优先级映射到数据分布。我们展示了对抗性自动编码器如何用于半监督分类、图像的风格和内容分解、无监督聚类、降维和数据可视化等应用。我们在MNIST、Street View House Numbers和Toronto Face数据集上进行了实验,结果表明,对抗性自编码器在生成建模和半监督分类任务中取得了有竞争力的结果。
How Wrong Am I? - Studying Adversarial Examples and their Impact on Uncertainty in Gaussian Process Machine Learning Models
机器学习模型容易受到对抗性样本的影响:对输入样本的微小扰动,故意造成错误分类。目前针对对抗性示例的防御,特别是深度神经网络(DNN),主要来自经验发展,其安全保证通常只能追溯性地证明。因此,许多防御依赖于隐藏的假设,这些假设随后被越来越复杂的攻击所颠覆。这并不奇怪:众所周知,深度学习缺乏一个全面的数学框架来提供有意义的保证。在本文中,我们利用高斯过程来研究贝叶斯推理框架中的对抗性示例。在不同的模型和数据集中,我们发现偏差水平的不确定性反映了最先进的攻击(包括对高斯过程的新型白盒攻击)引入到良性样本中的扰动。我们的实验表明,即使是未优化的不确定性阈值在许多情况下也会拒绝对抗性示例。备注:在arXiv:1812.02606(The limitations of model uncertainty in adversarial settings)中完成的修改攻击可以打破模型不确定性。
In this paper, we propose a defence strategy to improve adversarial robustness by incorporating hidden layer representation. The key of this defence strategy aims to compress or filter input information including adversarial perturbation. And this defence strategy can be regarded as an activation function which can be applied to any kind of neural network. We also prove theoretically the effectiveness of this defense strategy under certain conditions. Besides, incorporating hidden layer representation we propose three types of adversarial attacks to generate three types of adversarial examples…
Training Robust Deep Neural Networks via Adversarial Noise Propagation
Beihang University(北京航空航天大学);Beijing Advanced Innovation Center for Big Data-Based Precision Medicine(北京大数据精准医疗高精尖创新中心);University of Texas at Austin(德克萨斯大学奥斯汀分校);UBTECH Sydney Artificial Intelligence Centre(优必选悉尼人工智能中心);The University of Sydney(悉尼大学)
Adversarial Examples Detection with Bayesian Neural Network
University of North Carolina at Chapel Hill(北卡罗来纳大学教堂山分校);University of California Davis(加利福尼亚大学戴维斯分校);University of California Los Angeles(加利福尼亚大学洛杉矶分校)
Isik University(伊希克大学);University of Stavanger(斯塔万格大学)
In standard Deep Neural Network (DNN) based classifiers, the general convention is to omit the activation function in the last (output) layer and directly apply the softmax function on the logits to get the probability scores of each class. In this type of architectures, the loss value of the classifier against any output class is directly proportional to the difference between the final probability score and the label value of the associated class. Standard White-box adversarial evasion attacks, whether targeted or untargeted, mainly try to exploit the gradient of the model loss function to c…
Unveiling the Backdoor Mechanism Hidden Behind Catastrophic Overfitting in Fast Adversarial Training
School of Computer Science and Technology, Anhui University(安徽大学计算机科学与技术学院);School of Information and Communication Engineering, Dalian University of Technology(大连理工大学信息与通信工程学院);School of Computer Science and Technology, Zhejiang University(浙江大学计算机科学与技术学院)
Adversarial Defense by Restricting the Hidden Space of Deep Neural Networks
Inception Institute of Artificial Intelligence(起点人工智能研究院);University of Canberra(堪培拉大学);Australian National University(澳大利亚国立大学);Beijing Institute of Technology(北京理工大学)
Manipulating hidden-Markov-model inferences by corrupting batch data
United States Air Force Academy(美国空军学院);Institute of Mathematical Sciences (ICMAT)(数学科学研究所);McCoy College of Business, Texas State University(德克萨斯州立大学麦科伊商学院);CUNEF Universidad(库内夫大学)