Adversarial Attacks and Defense on Deep Learning Models for Big Data and IoT

2019 ◽  
pp. 39-66
Author(s):  
Nag Nami ◽  
Melody Moh
Keyword(s):  
Big Data ◽  
Deep Learning ◽  
Intelligent Systems ◽  
State Of The Art ◽  
Future Research ◽  
Human Intervention ◽  
Learning Models ◽  
Research Directions ◽  
Adversarial Examples ◽  
Future Research Directions

Intelligent systems are capable of doing tasks on their own with minimal or no human intervention. With the advent of big data and IoT, these intelligence systems have made their ways into most industries and homes. With its recent advancements, deep learning has created a niche in the technology space and is being actively used in big data and IoT systems globally. With the wider adoption, deep learning models unfortunately have become susceptible to attacks. Research has shown that many state-of-the-art accurate models can be vulnerable to attacks by well-crafted adversarial examples. This chapter aims to provide concise, in-depth understanding of attacks and defense of deep learning models. The chapter first presents the key architectures and application domains of deep learning and their vulnerabilities. Next, it illustrates the prominent adversarial examples, including the algorithms and techniques used to generate these attacks. Finally, it describes challenges and mechanisms to counter these attacks, and suggests future research directions.

scholarly journals Deep Learning Methods for Flood Mapping: A Review of Existing Applications and Future Research Directions

2021 ◽  
Author(s):  
Roberto Bentivoglio ◽  
Elvin Isufi ◽  
Sebastian Nicolaas Jonkman ◽  
Riccardo Taormina
Keyword(s):  
Deep Learning ◽  
Real Time ◽  
Case Studies ◽  
Flood Risk ◽  
Numerical Models ◽  
Flood Mapping ◽  
Future Research ◽  
Learning Models ◽  
Research Directions ◽  
Future Research Directions

Abstract. Deep Learning techniques have been increasingly used in flood risk management to overcome the limitations of accurate, yet slow, numerical models, and to improve the results of traditional methods for flood mapping. In this paper, we review 45 recent publications to outline the state-of-the-art of the field, identify knowledge gaps, and propose future research directions. The review focuses on the type of deep learning models used for various flood mapping applications, the flood types considered, the spatial scale of the studied events, and the data used for model development. The results show that models based on convolutional layers are usually more accurate as they leverage inductive biases to better process the spatial characteristics of the flooding events. Traditional models based on fully-connected layers, instead, provide accurate results when coupled with other statistical models. Deep learning models showed increased accuracy when compared to traditional approaches and increased speed when compared to numerical methods. While there exist several applications in flood susceptibility, inundation, and hazard mapping, more work is needed to understand how deep learning can assist real-time flood warning during an emergency, and how it can be employed to estimate flood risk. A major challenge lies in developing deep learning models that can generalize to unseen case studies and sites. Furthermore, all reviewed models and their outputs, are deterministic, with limited considerations for uncertainties in outcomes and probabilistic predictions. The authors argue that these identified gaps can be addressed by exploiting recent fundamental advancements in deep learning or by taking inspiration from developments in other applied areas. Models based on graph neural networks and neural operators can work with arbitrarily structured data and thus should be capable of generalizing across different case studies and could account for complex interactions with the natural and built environment. Neural operators can also speed up numerical models while preserving the underlying physical equations and could thus be used for reliable real-time warning. Similarly, probabilistic models can be built by resorting to Deep Gaussian Processes.

scholarly journals Deep Learning for Video Captioning: A Review

2019 ◽  
Author(s):  
Shaoxiang Chen ◽  
Ting Yao ◽  
Yu-Gang Jiang
Keyword(s):  
Deep Learning ◽  
Natural Language ◽  
Language Processing ◽  
State Of The Art ◽  
Future Research ◽  
Research Directions ◽  
Video Captioning ◽  
Future Research Directions ◽  
Review State ◽  
Vision And Language

Deep learning has achieved great successes in solving specific artificial intelligence problems recently. Substantial progresses are made on Computer Vision (CV) and Natural Language Processing (NLP). As a connection between the two worlds of vision and language, video captioning is the task of producing a natural-language utterance (usually a sentence) that describes the visual content of a video. The task is naturally decomposed into two sub-tasks. One is to encode a video via a thorough understanding and learn visual representation. The other is caption generation, which decodes the learned representation into a sequential sentence, word by word. In this survey, we first formulate the problem of video captioning, then review state-of-the-art methods categorized by their emphasis on vision or language, and followed by a summary of standard datasets and representative approaches. Finally, we highlight the challenges which are not yet fully understood in this task and present future research directions.

Cancer genotypes prediction and associations analysis from imaging phenotypes: a survey on radiogenomics

2020 ◽  
Vol 14 (12) ◽  
pp. 1151-1164
Author(s):  
Yao Wang ◽  
Yan Wang ◽  
Chunjie Guo ◽  
Xuping Xie ◽  
Sen Liang ◽  
...  
Keyword(s):  
Deep Learning ◽  
Statistical Analysis ◽  
Rapid Growth ◽  
Medical Data ◽  
Future Research ◽  
Strong Correlations ◽  
Learning Models ◽  
Research Directions ◽  
Application Potential ◽  
Future Research Directions

In this paper, we present a survey on the progress of radiogenomics research, which predicts cancer genotypes from imaging phenotypes and investigates the associations between them. First, we present an overview of the popular technology modalities for obtaining diagnostic medical images. Second, we summarize recently used methodologies for radiogenomics analysis, including statistical analysis, radiomics and deep learning. And then, we give a survey on the recent research based on several types of cancers. Finally, we discuss these studies and propose possible future research directions. In conclusion, we have identified strong correlations between cancer genotypes and imaging phenotypes. In addition, with the rapid growth of medical data, deep learning models show great application potential for radiogenomics.

Deep Learning--based Text Classification

2021 ◽  
Vol 54 (3) ◽  
pp. 1-40
Author(s):  
Shervin Minaee ◽  
Nal Kalchbrenner ◽  
Erik Cambria ◽  
Narjes Nikzad ◽  
Meysam Chenaghlu ◽  
...  
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Text Classification ◽  
Question Answering ◽  
Future Research ◽  
Learning Models ◽  
Research Directions ◽  
Comprehensive Review ◽  
Future Research Directions ◽  
Classification Tasks

Deep learning--based models have surpassed classical machine learning--based approaches in various text classification tasks, including sentiment analysis, news categorization, question answering, and natural language inference. In this article, we provide a comprehensive review of more than 150 deep learning--based models for text classification developed in recent years, and we discuss their technical contributions, similarities, and strengths. We also provide a summary of more than 40 popular datasets widely used for text classification. Finally, we provide a quantitative analysis of the performance of different deep learning models on popular benchmarks, and we discuss future research directions.

scholarly journals Social commerce—state-of-the-art and future research directions

2016 ◽  
Vol 26 (3) ◽  
pp. 269-290 ◽  
Author(s):  
Catherine Baethge ◽  
Julia Klier ◽  
Mathias Klier
Keyword(s):  
State Of The Art ◽  
Future Research ◽  
Social Commerce ◽  
Research Directions ◽  
Future Research Directions
Sign in / Sign up

Export Citation Format

Share Document