scholarly journals Securing Machine Learning in the Cloud: A Systematic Review of Cloud Machine Learning Security

2020 ◽  
Vol 3 ◽  
Author(s):  
Adnan Qayyum ◽  
Aneeqa Ijaz ◽  
Muhammad Usama ◽  
Waleed Iqbal ◽  
Junaid Qadir ◽  
...  
Keyword(s):  
Machine Learning ◽  
Systematic Review ◽  
Graphics Processing Units ◽  
High Performance ◽  
Cloud Services ◽  
Third Party ◽  
Systematic Evaluation ◽  
Research Issues ◽  
Wide Range ◽  
Attack And Defense

With the advances in machine learning (ML) and deep learning (DL) techniques, and the potency of cloud computing in offering services efficiently and cost-effectively, Machine Learning as a Service (MLaaS) cloud platforms have become popular. In addition, there is increasing adoption of third-party cloud services for outsourcing training of DL models, which requires substantial costly computational resources (e.g., high-performance graphics processing units (GPUs)). Such widespread usage of cloud-hosted ML/DL services opens a wide range of attack surfaces for adversaries to exploit the ML/DL system to achieve malicious goals. In this article, we conduct a systematic evaluation of literature of cloud-hosted ML/DL models along both the important dimensions—attacks and defenses—related to their security. Our systematic review identified a total of 31 related articles out of which 19 focused on attack, six focused on defense, and six focused on both attack and defense. Our evaluation reveals that there is an increasing interest from the research community on the perspective of attacking and defending different attacks on Machine Learning as a Service platforms. In addition, we identify the limitations and pitfalls of the analyzed articles and highlight open research issues that require further investigation.

Rapid 3D geological modeling to assess and visualize uncertainties in a web application

2021 ◽  
Author(s):  
Daniel Pflieger ◽  
Miguel de la Varga Hormazabal ◽  
Simon Virgo ◽  
Jan von Harten ◽  
Florian Wellmann
Keyword(s):  
Web Application ◽  
High Performance ◽  
Three Dimensional ◽  
Cloud Services ◽  
Management Approach ◽  
Geological Modeling ◽  
Web Browser ◽  
3D Geological Modeling ◽  
State Management ◽  
Wide Range

<p>Three dimensional modeling is a rapidly developing field in geological scientific and commercial applications. The combination of modeling and uncertainty analysis aides in understanding and quantitatively assessing complex subsurface structures. In recent years, many methods have been developed to facilitate this combined analysis, usually either through an extension of existing desktop applications or by making use of Jupyter notebooks as frontends. We evaluate here if modern web browser technology, linked to high-performance cloud services, can also be used for these types of analyses.</p><p>For this purpose, we developed a web application as proof-of-concept with the aim to visualize three dimensional geological models provided by a server. The implementation enables the modification of input parameters with assigned probability distributions. This step enables the generation of randomized realizations of models and the quantification and visualization of propagated uncertainties. The software is implemented using HTML Web Components on the client side and a Python server, providing a RESTful API to the open source geological modeling tool “GemPy”. Encapsulating the main components in custom elements, in combination with a minimalistic state management approach and a template parser, allows for high modularity. This enables rapid extendibility of the functionality of the components depending on the user’s needs and an easy integration into existing web platforms.</p><p>Our implementation shows that it is possible to extend and simplify modeling processes by creating an expandable web-based platform for probabilistic modeling, with the aim to increase the usability and to facilitate access to this functionality for a wide range of scientific analyses. The ability to compute models rapidly and with any given device in a web browser makes it flexible to use, and more accessible to a broader range of users.</p>

scholarly journals Astrophysical Supercomputing with GPUs: Critical Decisions for Early Adopters

2011 ◽  
Vol 28 (1) ◽  
pp. 15-27 ◽  
Author(s):  
Christopher J. Fluke ◽  
David G. Barnes ◽  
Benjamin R. Barsdell ◽  
Amr H. Hassan
Keyword(s):  
Graphics Processing Units ◽  
High Performance ◽  
Best Practice ◽  
New Technology ◽  
General Purpose ◽  
Third Party ◽  
Early Adopters ◽  
Early Adoption ◽  
Open Standard ◽  
Effective Use

AbstractGeneral-purpose computing on graphics processing units (GPGPU) is dramatically changing the landscape of high performance computing in astronomy. In this paper, we identify and investigate several key decision areas, with a goal of simplifying the early adoption of GPGPU in astronomy. We consider the merits of OpenCL as an open standard in order to reduce risks associated with coding in a native, vendor-specific programming environment, and present a GPU programming philosophy based on using brute force solutions. We assert that effective use of new GPU-based supercomputing facilities will require a change in approach from astronomers. This will likely include improved programming training, an increased need for software development best practice through the use of profiling and related optimisation tools, and a greater reliance on third-party code libraries. As with any new technology, those willing to take the risks and make the investment of time and effort to become early adopters of GPGPU in astronomy, stand to reap great benefits.

scholarly journals A Survey on Universal Adversarial Attack

2021 ◽  
Author(s):  
Chaoning Zhang ◽  
Philipp Benz ◽  
Chenguo Lin ◽  
Adil Karjauv ◽  
Jing Wu ◽  
...  
Keyword(s):  
Machine Learning ◽  
Recent Progress ◽  
New Findings ◽  
Wide Range ◽  
Adversarial Examples ◽  
Adversarial Attack ◽  
Attack And Defense ◽  
Audio Video ◽  
Significant Attention

The intriguing phenomenon of adversarial examples has attracted significant attention in machine learning and what might be more surprising to the community is the existence of universal adversarial perturbations (UAPs), i.e. a single perturbation to fool the target DNN for most images. With the focus on UAP against deep classifiers, this survey summarizes the recent progress on universal adversarial attacks, discussing the challenges from both the attack and defense sides, as well as the reason for the existence of UAP. We aim to extend this work as a dynamic survey that will regularly update its content to follow new works regarding UAP or universal attack in a wide range of domains, such as image, audio, video, text, etc. Relevant updates will be discussed at: https://bit.ly/2SbQlLG. We welcome authors of future works in this field to contact us for including your new findings.

Building High Performance Explainable Machine Learning Models for Social Media-based Substance Use Prediction

2020 ◽  
Vol 29 (03n04) ◽  
pp. 2060009
Author(s):  
Tao Ding ◽  
Fatema Hasan ◽  
Warren K. Bickel ◽  
Shimei Pan
Keyword(s):  
Machine Learning ◽  
Social Media ◽  
Substance Use ◽  
Human Behavior ◽  
High Performance ◽  
Supervised Machine Learning ◽  
Learning Models ◽  
Wide Range ◽  
And Behavior ◽  
Machine Learning Models

Social media contain rich information that can be used to help understand human mind and behavior. Social media data, however, are mostly unstructured (e.g., text and image) and a large number of features may be needed to represent them (e.g., we may need millions of unigrams to represent social media texts). Moreover, accurately assessing human behavior is often difficult (e.g., assessing addiction may require medical diagnosis). As a result, the ground truth data needed to train a supervised human behavior model are often difficult to obtain at a large scale. To avoid overfitting, many state-of-the-art behavior models employ sophisticated unsupervised or self-supervised machine learning methods to leverage a large amount of unsupervised data for both feature learning and dimension reduction. Unfortunately, despite their high performance, these advanced machine learning models often rely on latent features that are hard to explain. Since understanding the knowledge captured in these models is important to behavior scientists and public health providers, we explore new methods to build machine learning models that are not only accurate but also interpretable. We evaluate the effectiveness of the proposed methods in predicting Substance Use Disorders (SUD). We believe the methods we proposed are general and applicable to a wide range of data-driven human trait and behavior analysis applications.

scholarly journals A Grey-Box Ensemble Model Exploiting Black-Box Accuracy and White-Box Intrinsic Interpretability

Algorithms ◽  
2020 ◽  
Vol 13 (1) ◽  
pp. 17 ◽  
Author(s):  
Emmanuel Pintelas ◽  
Ioannis E. Livieris ◽  
Panagiotis Pintelas
Keyword(s):  
Machine Learning ◽  
Real World ◽  
High Performance ◽  
Black Box ◽  
Box Model ◽  
Proposed Model ◽  
Wide Range ◽  
Critical Issues ◽  
Key Factor ◽  
Real World Datasets

Machine learning has emerged as a key factor in many technological and scientific advances and applications. Much research has been devoted to developing high performance machine learning models, which are able to make very accurate predictions and decisions on a wide range of applications. Nevertheless, we still seek to understand and explain how these models work and make decisions. Explainability and interpretability in machine learning is a significant issue, since in most of real-world problems it is considered essential to understand and explain the model’s prediction mechanism in order to trust it and make decisions on critical issues. In this study, we developed a Grey-Box model based on semi-supervised methodology utilizing a self-training framework. The main objective of this work is the development of a both interpretable and accurate machine learning model, although this is a complex and challenging task. The proposed model was evaluated on a variety of real world datasets from the crucial application domains of education, finance and medicine. Our results demonstrate the efficiency of the proposed model performing comparable to a Black-Box and considerably outperforming single White-Box models, while at the same time remains as interpretable as a White-Box model.

scholarly journals A SURVEY OF TECHNIQUES FOR MANAGING AND LEVERAGING CACHES IN GPUs

2014 ◽  
Vol 23 (08) ◽  
pp. 1430002 ◽  
Author(s):  
SPARSH MITTAL
Keyword(s):  
Graphics Processing Units ◽  
High Performance ◽  
Heterogeneous Computing ◽  
General Purpose ◽  
System Level ◽  
Cache Management ◽  
Full Potential ◽  
Wide Range ◽  
Computing Platforms ◽  
Graphics Processing

Initially introduced as special-purpose accelerators for graphics applications, graphics processing units (GPUs) have now emerged as general purpose computing platforms for a wide range of applications. To address the requirements of these applications, modern GPUs include sizable hardware-managed caches. However, several factors, such as unique architecture of GPU, rise of CPU–GPU heterogeneous computing, etc., demand effective management of caches to achieve high performance and energy efficiency. Recently, several techniques have been proposed for this purpose. In this paper, we survey several architectural and system-level techniques proposed for managing and leveraging GPU caches. We also discuss the importance and challenges of cache management in GPUs. The aim of this paper is to provide the readers insights into cache management techniques for GPUs and motivate them to propose even better techniques for leveraging the full potential of caches in the GPUs of tomorrow.

scholarly journals Virtual to Real-World Transfer Learning: A Systematic Review

Electronics ◽  
2021 ◽  
Vol 10 (12) ◽  
pp. 1491
Author(s):  
Mahesh Ranaweera ◽  
Qusay H. Mahmoud
Keyword(s):  
Machine Learning ◽  
Systematic Review ◽  
Transfer Learning ◽  
Real World ◽  
High Performance ◽  
Research Area ◽  
Training Data ◽  
Machine Learning Techniques ◽  
Current Status ◽  
The Real

Machine learning has become an important research area in many domains and real-world applications. The prevailing assumption in traditional machine learning techniques, that training and testing data should be of the same domain, is a challenge. In the real world, gathering enough training data to create high-performance learning models is not easy. Sometimes data are not available, very expensive, or dangerous to collect. In this scenario, the concept of machine learning does not hold up to its potential. Transfer learning has recently gained much acclaim in the field of research as it has the capability to create high performance learners through virtual environments or by using data gathered from other domains. This systematic review defines (a) transfer learning; (b) discusses the recent research conducted; (c) the current status of transfer learning and finally, (d) discusses how transfer learning can bridge the gap between the virtual and the real.

scholarly journals [ANT]: A Machine Learning Approach for Building Performance Simulation: Methods and Development

2019 ◽  
Vol 3 (1) ◽  
pp. 205
Author(s):  
Mahmoud M. Abdelrahman ◽  
Ahmed Mohamed Yousef Toutou
Keyword(s):  
Machine Learning ◽  
High Performance ◽  
General Purpose ◽  
Ease Of Use ◽  
Building Performance ◽  
Performance Simulation ◽  
Building Performance Simulation ◽  
Wide Range ◽  
Performance Development ◽  
High Level

In this paper, we represent an approach for combining machine learning (ML) techniques with building performance simulation by introducing four methods in which ML could be effectively involved in this field i.e. Classification, Regression, Clustering and Model selection . Rhino-3d-Grasshopper SDK was used to develop a new plugin for involving machine learning in design process using Python programming language and making use of scikit-learn module, that is, a python module which provides a general purpose high level language to nonspecialist user by integration of wide range supervised and unsupervised learning algorithms with high performance, ease of use and well documented features. ANT plugin provides a method to make use of these modules inside Rhino\Grasshopper to be handy to designers. This tool is open source and is released under BSD simplified license. This approach represents promising results regarding making use of data in automating building performance development and could be widely applied. Future studies include providing parallel computation facility using PyOpenCL module as well as computer vision integration using scikit-image.

Configuring a Trusted Cloud Service Model for Smart City Exploration Using Hybrid Intelligence

2017 ◽  
Vol 8 (3) ◽  
pp. 1-21 ◽  
Author(s):  
Manash Sarkar ◽  
Soumya Banerjee ◽  
Youakim Badr ◽  
Arun Kumar Sangaiah
Keyword(s):  
Smart City ◽  
High Performance ◽  
Service Providers ◽  
Bat Algorithm ◽  
Cloud Service ◽  
Cloud Services ◽  
Third Party ◽  
Web Based ◽  
Proposed Model ◽  
Hybrid Intelligence

Emerging research concerns about the authenticated cloud service with high performance of security and assuring trust for distributed clients in a smart city. Cloud services are deployed by the third-party or web-based service providers. Thus, security and trust would be considered for every layer of cloud architecture. The principle objective of cloud service providers is to deliver better services with assurance of trust about clients' information. Cloud's users recurrently face different security challenges about the use of sharable resources. It is really difficult for Cloud Service Provider for adapting varieties of security policies to sustain their enterprises' goodwill. To make an optimistic decision that would be better suitable to provide a trusted cloud service for users' in smart city. Statistical method known as Multivariate Normal Distribution is used to select different attributes of different security entities for developing the proposed model. Finally, fuzzy multi objective decision making and Bio-Inspired Bat algorithm are applied to achieve the objective.

SIMULATING SPIN MODELS ON GPU: A TOUR

2012 ◽  
Vol 23 (08) ◽  
pp. 1240002 ◽  
Author(s):  
MARTIN WEIGEL
Keyword(s):  
Graphics Processing Units ◽  
High Performance ◽  
Heat Bath ◽  
Parallel Architecture ◽  
Recent Experience ◽  
Spin Models ◽  
Performance Per Watt ◽  
Wide Range ◽  
Lattice Spin Models ◽  
Graphics Processing

The use of graphics processing units (GPUs) in scientific computing has gathered considerable momentum in the past five years. While GPUs in general promise high performance and excellent performance per Watt ratios, not every class of problems is equally well suitable for exploiting the massively parallel architecture they provide. Lattice spin models appear to be prototypic examples of problems suitable for this architecture, at least as long as local update algorithms are employed. In this review, I summarize our recent experience with the simulation of a wide range of spin models on GPU employing an equally wide range of update algorithms, ranging from Metropolis and heat bath updates, over cluster algorithms to generalized ensemble simulations.

Sign in / Sign up

Export Citation Format

Share Document