Institution
University of Colorado Colorado Springs
Education•Colorado Springs, Colorado, United States•
About: University of Colorado Colorado Springs is a education organization based out in Colorado Springs, Colorado, United States. It is known for research contribution in the topics: Population & Poison control. The organization has 6664 authors who have published 10872 publications receiving 323416 citations. The organization is also known as: UCCS & University of Colorado at Colorado Springs.
Topics: Population, Poison control, Thin film, Capacitor, Ferroelectricity
Papers published on a yearly basis
Papers
More filters
••
05 May 2016TL;DR: In this article, the authors introduce a hot/cold approach for adversarial example generation, which provides multiple possible adversarial perturbations for every single image, and demonstrate that fine-tuning with a diverse set of hard positives improves the robustness of these networks compared to training with prior methods of generating adversarial images.
Abstract: State-of-the-art deep neural networks suffer from a fundamental problem – they misclassify adversarial examples formed by applying small perturbations to inputs. In this paper, we present a new psychometric perceptual adversarial similarity score (PASS) measure for quantifying adversarial images, introduce the notion of hard positive generation, and use a diverse set of adversarial perturbations – not just the closest ones – for data augmentation. We introduce a novel hot/cold approach for adversarial example generation, which provides multiple possible adversarial perturbations for every single image. The perturbations generated by our novel approach often correspond to semantically meaningful image structures, and allow greater flexibility to scale perturbation-amplitudes, which yields an increased diversity of adversarial images. We present adversarial images on several network topologies and datasets, including LeNet on the MNIST dataset, and GoogLeNet and ResidualNet on the ImageNet dataset. Finally, we demonstrate on LeNet and GoogLeNet that fine-tuning with a diverse set of hard positives improves the robustness of these networks compared to training with prior methods of generating adversarial images.
271 citations
••
TL;DR: Not each level of maturity demonstrated observable benefits, indicating that greater caution is needed in the planning and implementation of the activities, and performance of projects in relation to the activities at these various levels of maturity.
269 citations
••
TL;DR: A terror management analysis of the psychological function of structuring social information found that mortality salience increased high-PNS participants' preference for interpretations that suggest a just world and a benevolent causal order of events in the social world.
Abstract: Drawing on lay epistemology theory, the authors assessed a terror management analysis of the psychological function of structuring social information. Seven studies tested variations of the hypothesis that simple, benign interpretations of social information function, in part, to manage death-related anxiety. In Studies 1-4, mortality salience (MS) exaggerated primacy effects and reliance on representative information, decreased preference for a behaviorally inconsistent target among those high in personal need for structure (PNS), and increased high-PNS participants' preference for interpersonal balance. In Studies 5-7, MS increased high-PNS participants' preference for interpretations that suggest a just world and a benevolent causal order of events in the social world.
269 citations
••
TL;DR: In this paper, the authors review past transitions and factors behind them, along with their time frames, and identify several policy instruments to accelerate a transition, though even under ideal circumstances a global energy supply transition will be very slow.
267 citations
••
TL;DR: The emerging field of digital image forensics is introduced, including the main topic areas of source camera identification, forgery detection, and steganalysis, including a critical analysis of the state of the art, and recommendations for the direction of future research.
Abstract: Digital images are everywhere—from our cell phones to the pages of our online news sites. How we choose to use digital image processing raises a surprising host of legal and ethical questions that we must address. What are the ramifications of hiding data within an innocent imageq Is this an intentional security practice when used legitimately, or intentional deceptionq Is tampering with an image appropriate in cases where the image might affect public behaviorq Does an image represent a crime, or is it simply a representation of a scene that has never existedq Before action can even be taken on the basis of a questionable image, we must detect something about the image itself. Investigators from a diverse set of fields require the best possible tools to tackle the challenges presented by the malicious use of today's digital image processing techniques.In this survey, we introduce the emerging field of digital image forensics, including the main topic areas of source camera identification, forgery detection, and steganalysis. In source camera identification, we seek to identify the particular model of a camera, or the exact camera, that produced an image. Forgery detection's goal is to establish the authenticity of an image, or to expose any potential tampering the image might have undergone. With steganalysis, the detection of hidden data within an image is performed, with a possible attempt to recover any detected data. Each of these components of digital image forensics is described in detail, along with a critical analysis of the state of the art, and recommendations for the direction of future research.
266 citations
Authors
Showing all 6706 results
Name | H-index | Papers | Citations |
---|---|---|---|
Jeff Greenberg | 105 | 542 | 43600 |
James F. Scott | 99 | 714 | 58515 |
Martin Wikelski | 89 | 420 | 25821 |
Neil W. Kowall | 89 | 279 | 34943 |
Ananth Dodabalapur | 85 | 394 | 27246 |
Tom Pyszczynski | 82 | 246 | 30590 |
Patrick S. Kamath | 78 | 466 | 31281 |
Connie M. Weaver | 77 | 473 | 30985 |
Alejandro Lucia | 75 | 680 | 23967 |
Michael J. McKenna | 70 | 356 | 16227 |
Timothy J. Craig | 69 | 458 | 18340 |
Sheldon Solomon | 67 | 150 | 23916 |
Michael H. Stone | 65 | 370 | 16355 |
Christopher J. Gostout | 65 | 334 | 13593 |
Edward T. Ryan | 60 | 303 | 11822 |