We present a novel adversarial detection and correction method for machine learning classifiers.The detector consists of an autoencoder trained with a custom loss function based on the Kullback-Leibler divergence between the classifier predictions on the original and reconstructed instances.The method is unsupervised, easy to train and does not require any knowledge about the underlying attack. The detector almost completely neutralises powerful attacks like Carlini-Wagner or SLIDE on MNIST and Fashion-MNIST, and remains very effective on CIFAR-10 when the attack is granted full access to the classification model but not the defence. We show that our method is still able to detect the adversarial examples in the case of a white-box attack where the attacker has full knowledge of both the model and the defence and investigate the robustness of the attack. The method is very flexible and can also be used to detect common data corruptions and perturbations which negatively impact the model performance. We illustrate this capability on the CIFAR-10-C dataset.
Partial Distribution Matching via Partial Wasserstein Adversarial Networks
Department of Mathematical Sciences, University of Chalmers（楚尔姆斯大学数学科学系）；Ant Group（蚂蚁集团）；School of Mathematics and Statistics（数学与统计学学院）；School of Computer Science（计算机科学学院）；National Engineering Research Center for Multimedia Software (NERCMS)（多媒体软件国家工程研究中心）；Institute for Mathematics and Artificial Intelligence（数学与人工智能研究院）
University of Montreal（蒙特利尔大学）；Microsoft Research Lab（微软研究院实验室）
Denoising Score Matching with Annealed Langevin Sampling (DSM-ALS) has recently found success in generative modeling. The approach works by first training a neural network to estimate the score of a distribution, and then using Langevin dynamics to sample from the data distribution assumed by the score network. Despite the convincing visual quality of samples, this method appears to perform worse than Generative Adversarial Networks (GANs) under the Fréchet Inception Distance, a standard metric for generative models. We show that this apparent gap vanishes when denoising the final Langevin sam…
University of Sussex（萨塞克斯大学）；BCAM Severo Ochoa Strategic Lab on Trustworthy Machine Learning（BCAM塞韦罗·奥乔亚可信机器学习战略实验室）
When trained on diverse labeled data, machine learning models have proven themselves to be a powerful tool in all facets of society. However, due to budget limitations, deliberate or non-deliberate censorship, and other problems during data collection and curation, the labeled training set might exhibit a systematic shortage of data for certain groups. We investigate a scenario in which the absence of certain data is linked to the second level of a two-level hierarchy in the data. Inspired by the idea of protected groups from algorithmic fairness, we refer to the partitions carved by this seco…
With the widespread use of machine learning, concerns over its security and reliability have become prevalent. As such, many have developed defenses to harden neural networks against adversarial examples, imperceptibly perturbed inputs that are reliably misclassified. Adversarial training in which adversarial examples are generated and used during training is one of the few known defenses able to reliably withstand such attacks against neural networks. However, adversarial training imposes a significant training overhead and scales poorly with model complexity and input dimension. In this pape…
Deep Imitation Learning requires a large number of expert demonstrations, which are not always easy to obtain, especially for complex tasks. A way to overcome this shortage of labels is through data augmentation. However, this cannot be easily applied to control tasks due to the sequential nature of the problem. In this work, we introduce a novel augmentation method which preserves the success of the augmented trajectories. To achieve this, we introduce a semi-supervised correction network that aims to correct distorted expert actions. To adequately test the abilities of the correction network…
University of Concepción（康塞普西翁大学）；Harvard University（哈佛大学）；University of Chile（智利大学）
In this work we address the problem of transferring knowledge obtained from a vast annotated source domain to a low labeled target domain. We propose Adversarial Variational Domain Adaptation (AVDA), a semi-supervised domain adaptation method based on deep variational embedded representations. We use approximate inference and domain adversarial methods to map samples from source and target domains into an aligned class-dependent embedding defined as a Gaussian Mixture Model. AVDA works as a classifier and considers a generative model that helps this classification. We used digits dataset for e…
University of North Carolina Charlotte（北卡罗来纳大学夏洛特分校）；Montreal Institute for Learning Algorithms（蒙特利尔学习算法研究所）；Carnegie Mellon University（卡内基梅隆大学）；University of Maryland College Park（马里兰大学学院公园分校）；Korea University（高丽大学）；IIIT Delhi（德里印度理工学院）；Electronics and Telecommunications Research Institute（电子与电信研究院）
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。
Recent works in Grammatical Error Correction (GEC) have leveraged the progress in Neural Machine Translation (NMT), to learn rewrites from parallel corpora of grammatically incorrect and corrected sentences, achieving state-of-the-art results. At the same time, Generative Adversarial Networks (GANs) have been successful in generating realistic texts across many different tasks by learning to directly minimize the difference between human-generated and synthetic text. In this work, we present an adversarial learning approach to GEC, using the generator-discriminator framework. The generator is …
CMR motion artifact correction using generative adversarial nets
Research Institute of Information Technology.Tsinghua University（清华大学信息技术研究院）；Automation School.Beijing University of Posts and Telecommunications（北京邮电大学自动化学院）；MRI Center.Fuwai Hospital.Chinese Academy of Medical Science（中国医学科学院阜外医院MRI中心）
心血管磁共振（Cardiovascular Magnetic Resonance，CMR）在心血管疾病的诊断和治疗中发挥着重要作用，而CMR扫描过程中形成的运动伪影严重影响医生对病灶的准确定位。目前的校正方法主要集中在K空间，这是一个网格的原始数据直接从MR信号，然后转移到CMR图像通过逆傅立叶变换。它们既不有效也不高效，不能用于临床。在本文中，我们提出了一种使用深度学习进行CMR运动伪影校正的新方法。特别地，我们使用深度残差网络（ResNet）作为网络框架，并以对抗的方式对我们的模型进行训练。我们的方法的动机是图像运动模糊和CMR运动伪影之间的联系，因此我们可以将深度学习已经取得很大进展的运动去模糊方法成功地转移到CMR运动校正。为了评估运动伪影校正方法，我们提出了一种新的算法，如何通过去模糊算法改善边缘检测结果。在深度学习和对抗训练算法的推动下，我们的模型可以端到端的方式训练，可以实时测试，并实现CMR校正的最新结果。
Open-Set Domain Adaptation (OSDA) assumes that a target domain contains unknown classes, which are not discovered in a source domain. Existing domain adversarial learning methods are not suitable for OSDA because distribution matching with $\textit{unknown}$ classes leads to negative transfer. Previous OSDA methods have focused on matching the source and the target distribution by only utilizing $\textit{known}$ classes. However, this $\textit{known}$-only matching may fail to learn the target-$\textit{unknown}$ feature space. Therefore, we propose Unknown-Aware Domain Adversarial Learning (UA…
University of Toronto（多伦多大学）；Canadian Institute for Advanced Research（加拿大高等研究院）
我们考虑从数据中学习深度生成模型的问题。我们制定了一种方法，该方法通过多层感知器的单次前馈来生成独立样本，如最近提出的生成对抗网络（Goodfellow et al.，2014年）。然而，训练一个生成对抗网络需要仔细优化一个困难的极小极大程序。相反，我们利用了一种被称为最大平均差异（MMD）的统计假设检验技术，这导致了一个简单的目标，可以被解释为匹配数据集和模型样本之间的所有统计阶数，并且可以通过反向传播进行训练。我们通过将我们的生成网络与自动编码器网络相结合，使用MMD来学习生成代码，然后可以解码生成样本，从而进一步提高了这种方法的性能。我们表明，这些技术的组合产生优秀的生成模型相比，MNIST和多伦多人脸数据库上测量的基线方法。
Two-sided matching markets have long existed to pair agents in the absence of regulated exchanges. A common example is school choice, where a matching mechanism uses student and school preferences to assign students to schools. In such settings, forming preferences is both difficult and critical. Prior work has suggested various prediction mechanisms that help agents make decisions about their preferences. Although often deployed together, these matching and prediction mechanisms are almost always analyzed separately. The present work shows that at the intersection of the two lies a previously…
The interplay between quantum physics and machine learning gives rise to the emergent frontier of quantum machine learning, where advanced quantum learning models may outperform their classical counterparts in solving certain challenging problems. However, quantum learning systems are vulnerable to adversarial attacks: adding tiny carefully-crafted perturbations on legitimate input samples can cause misclassifications. To address this issue, we propose a general scheme to protect quantum learning systems from adversarial attacks by randomly encoding the legitimate data samples through unitary …
Grammatical Error Correction (GEC) systems perform a sequence-to-sequence task, where an input word sequence containing grammatical errors, is corrected for these errors by the GEC system to output a grammatically correct word sequence. With the advent of deep learning methods, automated GEC systems have become increasingly popular. For example, GEC systems are often used on speech transcriptions of English learners as a form of assessment and feedback - these powerful GEC systems can be used to automatically measure an aspect of a candidate's fluency. The count of \textit{edits} from a candid…
HURRI-GAN: A Novel Approach for Hurricane Bias-Correction Beyond Gauge Stations using Generative Adversarial Networks
Center of Computation and Technology, Louisiana State University（路易斯安那州立大学计算与技术中心）；Saint-Joseph University of Beirut（贝鲁特圣约瑟夫大学）；Department of Physics, Aristotle University of Thessaloniki（塞萨洛尼基阿列克斯大学物理系）；Center for Interdisciplinary Research and Innovation, Aristotle University of Thessaloniki（塞萨洛尼基阿列克斯大学跨学科研究中心）；Department of Computer Science, Louisiana State University（路易斯安那州立大学计算机科学系）；Oden Institute for Computational Engineering and Sciences, The University of Texas at Austin（德克萨斯大学奥斯汀分校奥登计算工程与科学研究院）
