Institution
Carnegie Mellon University
Education•Pittsburgh, Pennsylvania, United States•
About: Carnegie Mellon University is a education organization based out in Pittsburgh, Pennsylvania, United States. It is known for research contribution in the topics: Population & Robot. The organization has 36317 authors who have published 104359 publications receiving 5975734 citations. The organization is also known as: CMU & Carnegie Mellon.
Papers published on a yearly basis
Papers
More filters
••
12 Oct 2015TL;DR: A new class of model inversion attack is developed that exploits confidence values revealed along with predictions and is able to estimate whether a respondent in a lifestyle survey admitted to cheating on their significant other and recover recognizable images of people's faces given only their name.
Abstract: Machine-learning (ML) algorithms are increasingly utilized in privacy-sensitive applications such as predicting lifestyle choices, making medical diagnoses, and facial recognition. In a model inversion attack, recently introduced in a case study of linear classifiers in personalized medicine by Fredrikson et al., adversarial access to an ML model is abused to learn sensitive genomic information about individuals. Whether model inversion attacks apply to settings outside theirs, however, is unknown. We develop a new class of model inversion attack that exploits confidence values revealed along with predictions. Our new attacks are applicable in a variety of settings, and we explore two in depth: decision trees for lifestyle surveys as used on machine-learning-as-a-service systems and neural networks for facial recognition. In both cases confidence values are revealed to those with the ability to make prediction queries to models. We experimentally show attacks that are able to estimate whether a respondent in a lifestyle survey admitted to cheating on their significant other and, in the other context, show how to recover recognizable images of people's faces given only their name and access to the ML model. We also initiate experimental exploration of natural countermeasures, investigating a privacy-aware decision tree training algorithm that is a simple variant of CART learning, as well as revealing only rounded confidence values. The lesson that emerges is that one can avoid these kinds of MI attacks with negligible degradation to utility.
2,156 citations
••
07 Dec 2015TL;DR: In this paper, the spatial context is used as a source of free and plentiful supervisory signal for training a rich visual representation, and the feature representation learned using this within-image context captures visual similarity across images.
Abstract: This work explores the use of spatial context as a source of free and plentiful supervisory signal for training a rich visual representation. Given only a large, unlabeled image collection, we extract random pairs of patches from each image and train a convolutional neural net to predict the position of the second patch relative to the first. We argue that doing well on this task requires the model to learn to recognize objects and their parts. We demonstrate that the feature representation learned using this within-image context indeed captures visual similarity across images. For example, this representation allows us to perform unsupervised visual discovery of objects like cats, people, and even birds from the Pascal VOC 2011 detection dataset. Furthermore, we show that the learned ConvNet can be used in the R-CNN framework [19] and provides a significant boost over a randomly-initialized ConvNet, resulting in state-of-the-art performance among algorithms which use only Pascal-provided training set annotations.
2,154 citations
•
TL;DR: The API design and the system implementation of MXNet are described, and it is explained how embedding of both symbolic expression and tensor operation is handled in a unified fashion.
Abstract: MXNet is a multi-language machine learning (ML) library to ease the development of ML algorithms, especially for deep neural networks. Embedded in the host language, it blends declarative symbolic expression with imperative tensor computation. It offers auto differentiation to derive gradients. MXNet is computation and memory efficient and runs on various heterogeneous systems, ranging from mobile devices to distributed GPU clusters.
This paper describes both the API design and the system implementation of MXNet, and explains how embedding of both symbolic expression and tensor operation is handled in a unified fashion. Our preliminary experiments reveal promising results on large scale deep neural network applications using multiple GPU machines.
2,153 citations
••
TL;DR: This review summarizes the major progress in the field, including the principles that permit atomically precise synthesis, new types of atomic structures, and unique physical and chemical properties ofatomically precise nanoparticles, as well as exciting opportunities for nanochemists to understand very fundamental science of colloidal nanoparticles.
Abstract: Colloidal nanoparticles are being intensely pursued in current nanoscience research. Nanochemists are often frustrated by the well-known fact that no two nanoparticles are the same, which precludes the deep understanding of many fundamental properties of colloidal nanoparticles in which the total structures (core plus surface) must be known. Therefore, controlling nanoparticles with atomic precision and solving their total structures have long been major dreams for nanochemists. Recently, these goals are partially fulfilled in the case of gold nanoparticles, at least in the ultrasmall size regime (1–3 nm in diameter, often called nanoclusters). This review summarizes the major progress in the field, including the principles that permit atomically precise synthesis, new types of atomic structures, and unique physical and chemical properties of atomically precise nanoparticles, as well as exciting opportunities for nanochemists to understand very fundamental science of colloidal nanoparticles (such as the s...
2,144 citations
••
University of Southern California1, French Institute for Research in Computer Science and Automation2, University of Oulu3, Princeton University4, University of Warwick5, Georgia Institute of Technology6, Rutgers University7, University of Virginia8, University of Washington9, Carnegie Mellon University10, École Polytechnique Fédérale de Lausanne11, University of Pittsburgh12, University of Wisconsin-Madison13, University of California, San Diego14, University of Illinois at Urbana–Champaign15, Nanyang Technological University16, Australian National University17, Stanford University18, IT University of Copenhagen19, Massachusetts Institute of Technology20, University of California, Berkeley21, Cornell University22, Emory University23, Hong Kong University of Science and Technology24
TL;DR: In this article, the authors describe the state-of-the-art in the field of federated learning from the perspective of distributed optimization, cryptography, security, differential privacy, fairness, compressed sensing, systems, information theory, and statistics.
Abstract: The term Federated Learning was coined as recently as 2016 to describe a machine learning setting where multiple entities collaborate in solving a machine learning problem, under the coordination of a central server or service provider. Each client’s raw data is stored locally and not exchanged or transferred; instead, focused updates intended for immediate aggregation are used to achieve the learning objective. Since then, the topic has gathered much interest across many different disciplines and the realization that solving many of these interdisciplinary problems likely requires not just machine learning but techniques from distributed optimization, cryptography, security, differential privacy, fairness, compressed sensing, systems, information theory, statistics, and more. This monograph has contributions from leading experts across the disciplines, who describe the latest state-of-the art from their perspective. These contributions have been carefully curated into a comprehensive treatment that enables the reader to understand the work that has been done and get pointers to where effort is required to solve many of the problems before Federated Learning can become a reality in practical systems. Researchers working in the area of distributed systems will find this monograph an enlightening read that may inspire them to work on the many challenging issues that are outlined. This monograph will get the reader up to speed quickly and easily on what is likely to become an increasingly important topic: Federated Learning.
2,144 citations
Authors
Showing all 36645 results
Name | H-index | Papers | Citations |
---|---|---|---|
Yi Chen | 217 | 4342 | 293080 |
Rakesh K. Jain | 200 | 1467 | 177727 |
Robert C. Nichol | 187 | 851 | 162994 |
Michael I. Jordan | 176 | 1016 | 216204 |
Jasvinder A. Singh | 176 | 2382 | 223370 |
J. N. Butler | 172 | 2525 | 175561 |
P. Chang | 170 | 2154 | 151783 |
Krzysztof Matyjaszewski | 169 | 1431 | 128585 |
Yang Yang | 164 | 2704 | 144071 |
Geoffrey E. Hinton | 157 | 414 | 409047 |
Herbert A. Simon | 157 | 745 | 194597 |
Yongsun Kim | 156 | 2588 | 145619 |
Terrence J. Sejnowski | 155 | 845 | 117382 |
John B. Goodenough | 151 | 1064 | 113741 |
Scott Shenker | 150 | 454 | 118017 |