國立高雄大學圖資館 |

Language: English

Back

Deep Learning for Image Steganography and Steganalysis Challenges, Advances, and Opportunities.

Record Type:	Electronic resources : Monograph/item
Title/Author:	Deep Learning for Image Steganography and Steganalysis Challenges, Advances, and Opportunities.
Author:	Yousfi, Yassine.
Published:	Ann Arbor : ProQuest Dissertations & Theses, 2022
Description:	135 p.
Notes:	Source: Dissertations Abstracts International, Volume: 84-01, Section: B.
Notes:	Advisor: Fridrich, Jessica.
Contained By:	Dissertations Abstracts International84-01B.
Subject:	Computer science.
Online resource:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=29209948
ISBN:	9798834049692

Deep Learning for Image Steganography and Steganalysis Challenges, Advances, and Opportunities.
Yousfi, Yassine.

Deep Learning for Image Steganography and Steganalysis Challenges, Advances, and Opportunities. - Ann Arbor : ProQuest Dissertations & Theses, 2022 - 135 p.

Source: Dissertations Abstracts International, Volume: 84-01, Section: B.

Thesis (Ph.D.)--State University of New York at Binghamton, 2022.

This item must not be sold to any third party vendors.

Deep learning has proven incredibly successful in a plethora of fields. In computer vision, deep neural networks are now the state-of-the-art for a variety of tasks. At the first glance, steganography and steganalysis appear to be very much different tasks than classical computer vision tasks, yet deep learning, especially convolutional neural networks, popularized by the computer vision field, have outperformed all classical feature-based approaches for detecting steganography. Intuitively, steganographic embedding changes are weak, noise-like signals executed primarily in complex content, such as textures and edges. Since computer vision classifies and categorizes content, it is also suitable for detecting the presence of noise-like stego signals modulated by content.In this dissertation, we focus on refactoring steganography detectors with more modern and general components, qualitatively understanding their strengths and failure cases, and using them algorithmically to improve steganography. First, we show that many custom ingredients long believed to be necessary for successfully training a deep neural network for steganography detection can be omitted in favor of more general-purpose convolutional architectures with very few domain-specific changes. Next, we focus on understanding what makes deep neural networks superior to their classical feature-based predecessors. Lastly, we use these powerful steganography detectors as a feedback loop in novel batch steganography algorithms, which allocate more payload in images where state-of-the-art detectors fail to detect steganography.

ISBN: 9798834049692Subjects--Topical Terms:

199325
Computer science.
Subjects--Index Terms:

Deep learning

Deep Learning for Image Steganography and Steganalysis Challenges, Advances, and Opportunities.
LDR:02858nmm a2200397 4500 001 636120
005 20230501063904.5
006 m o d
007 cr#unu||||||||
008 230724s2022 ||||||||||||||||| ||eng d
020 $a 9798834049692
035 $a (MiAaPQ)AAI29209948
035 $a AAI29209948
040 $a MiAaPQ $c MiAaPQ
100 1 $a Yousfi, Yassine. $3 942450
245 1 0 $a Deep Learning for Image Steganography and Steganalysis Challenges, Advances, and Opportunities.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2022
300 $a 135 p.
500 $a Source: Dissertations Abstracts International, Volume: 84-01, Section: B.
500 $a Advisor: Fridrich, Jessica.
502 $a Thesis (Ph.D.)--State University of New York at Binghamton, 2022.
506 $a This item must not be sold to any third party vendors.
520 $a Deep learning has proven incredibly successful in a plethora of fields. In computer vision, deep neural networks are now the state-of-the-art for a variety of tasks. At the first glance, steganography and steganalysis appear to be very much different tasks than classical computer vision tasks, yet deep learning, especially convolutional neural networks, popularized by the computer vision field, have outperformed all classical feature-based approaches for detecting steganography. Intuitively, steganographic embedding changes are weak, noise-like signals executed primarily in complex content, such as textures and edges. Since computer vision classifies and categorizes content, it is also suitable for detecting the presence of noise-like stego signals modulated by content.In this dissertation, we focus on refactoring steganography detectors with more modern and general components, qualitatively understanding their strengths and failure cases, and using them algorithmically to improve steganography. First, we show that many custom ingredients long believed to be necessary for successfully training a deep neural network for steganography detection can be omitted in favor of more general-purpose convolutional architectures with very few domain-specific changes. Next, we focus on understanding what makes deep neural networks superior to their classical feature-based predecessors. Lastly, we use these powerful steganography detectors as a feedback loop in novel batch steganography algorithms, which allocate more payload in images where state-of-the-art detectors fail to detect steganography.
590 $a School code: 0792.
650 4 $a Computer science. $3 199325
650 4 $a Information science. $3 190425
650 4 $a Artificial intelligence. $3 194058
653 $a Deep learning
653 $a Steganalysis
653 $a Steganography
653 $a Computer vision
653 $a Cybersecurity
690 $a 0984
690 $a 0723
690 $a 0800
710 2 $a State University of New York at Binghamton. $b Electrical and Computer Engineering. $3 915677
773 0 $t Dissertations Abstracts International $g 84-01B.
790 $a 0792
791 $a Ph.D.
792 $a 2022
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=29209948