Recent Advances in AI-Based Multimedia Security and Protection with Symmetry

A special issue of Symmetry (ISSN 2073-8994). This special issue belongs to the section "Computer".

Deadline for manuscript submissions: closed (2 October 2023) | Viewed by 3283

Special Issue Editors

Department of Electronic and Information Engineering, Shanghai University, Shanghai 200444, China
Interests: multimedia security; security and communication networks
School of Optical-Electrical and Computer Engineering, University of Shanghai for Science and Technology, Shanghai 200093, China
Interests: multimedia security; image processing; AI security
Special Issues, Collections and Topics in MDPI journals
College of Computer Science and Technology, Shanghai University of Electric Power, Shanghai 200090, China
Interests: multimedia security; information hiding; steganography and steganalysis

Special Issue Information

Dear Colleagues,

In recent years, with the rapid development of artificial intelligence (AI) technology, a user can easily process multimedia content using various deep neural networks, e.g., CNN and GAN, and accordingly pose a serious challenge to personal privacy protection and information security. Correspondingly, AI-based multimedia security and protection research has been attracting a lot of interest. In general, multimedia protection and detection issues can always be regarded as a symmetrical signal processing model. Secret data are embedded into multimedia files via a series of signal processing methods to achieve covert communication, copyright protection, and authentication, whereas the corresponding detection technique is an inverse technology, which is mainly to discover the presence of secret data or the presence of illegal tampering behavior. Remarkable works have emerged around this theme in recent years. Nevertheless, a series of problems still exist in the relevant fields, especially in social multimedia forensics, steganography and steganalysis, digital watermarking, network privacy protection, AI security, etc.

This Special Issue aims to contribute state-of-the-art original research outcomes toward AI-based multimedia security and protection and provide advanced methods or engineering applications for researchers and engineers. All submitted papers will be peer-reviewed and selected on the basis of both their quality and relevance to the topics of this Special Issue.

Potential topics include but are not limited to:

  • Symmetry theory of information hiding;
  • Steganography and steganalysis;
  • Digital watermarking in multimedia;
  • Symmetry issues in reversible data hiding;
  • Fake multimedia forensics and anti-forensics;
  • AI-based multimedia generation and detection;
  • AI-based deepfake videos and detection;
  • AI-based multimedia authentication;
  • Symmetry/asymmetry theory in multimedia encryption;
  • Symmetry and heuristic in multimedia protection;
  • Privacy and security issues in multimedia cloud;
  • Symmetry and multimedia protection applications.

Dr. Hanzhou Wu
Dr. Chuan Qin
Prof. Dr. Fengyong Li
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Symmetry is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • data hiding
  • steganography
  • steganalysis
  • watermarking
  • deepfake
  • multimedia encryption
  • multimedia forensics
  • multimedia hashing
  • adversarial sample

Published Papers (2 papers)

Order results
Result details
Select all
Export citation of selected articles as:

Research

12 pages, 8017 KiB  
Article
DIGDH: A Novel Framework of Difference Image Grafting Deep Hiding for Image Data Hiding
by Xintao Duan, Lei Li, Yao Su, Wenxin Wang, En Zhang and Xianfang Wang
Symmetry 2022, 14(1), 151; https://doi.org/10.3390/sym14010151 - 13 Jan 2022
Viewed by 1180
Abstract
Data hiding is the technique of embedding data into video or audio media. With the development of deep neural networks (DNN), the quality of images generated by novel data hiding methods based on DNN is getting better. However, there is still room for [...] Read more.
Data hiding is the technique of embedding data into video or audio media. With the development of deep neural networks (DNN), the quality of images generated by novel data hiding methods based on DNN is getting better. However, there is still room for the similarity between the original images and the images generated by the DNN models which were trained based on the existing hiding frameworks to improve, and it is hard for the receiver to distinguish whether the container image is from the real sender. We propose a framework by introducing a key_img for using the over-fitting characteristic of DNN and combined with difference image grafting symmetrically, named difference image grafting deep hiding (DIGDH). The key_img can be used to identify whether the container image is from the real sender easily. The experimental results show that without changing the structures of networks, the models trained based on the proposed framework can generate images with higher similarity to original cover and secret images. According to the analysis results of the steganalysis tool named StegExpose, the container images generated by the hiding model trained based on the proposed framework is closer to the random distribution. Full article
Show Figures

Figure 1

18 pages, 1153 KiB  
Article
A Novel High-Capacity Behavioral Steganographic Method Combining Timestamp Modulation and Carrier Selection Based on Social Networks
by Mingliang Zhang, Zhenyu Li, Pei Zhang, Yi Zhang and Xiangyang Luo
Symmetry 2022, 14(1), 111; https://doi.org/10.3390/sym14010111 - 08 Jan 2022
Cited by 1 | Viewed by 1148
Abstract
Behavioral steganography is a method used to achieve covert communication based on the sender’s behaviors. It has attracted a great deal of attention due to its robustness and wide application scenarios. Current behavioral steganographic methods are still difficult to apply in practice because [...] Read more.
Behavioral steganography is a method used to achieve covert communication based on the sender’s behaviors. It has attracted a great deal of attention due to its robustness and wide application scenarios. Current behavioral steganographic methods are still difficult to apply in practice because of their limited embedding capacity. To this end, this paper proposes a novel high-capacity behavioral steganographic method combining timestamp modulation and carrier selection based on social networks. It is a steganographic method where the embedding process and the extraction process are symmetric. When sending a secret message, the method first maps the secret message to a set of high-frequency keywords and divides them into keyword subsets. Then, the posts containing the keyword subsets are retrieved on social networks. Next, the positions of the keywords in the posts are modulated as the timestamps. Finally, the stego behaviors applied to the retrieved posts are generated. This method does not modify the content of the carrier, which ensures the naturalness of the posts. Compared with typical behavioral steganographic methods, the embedding capacity of the proposed method is 29.23∼51.47 times higher than that of others. Compared to generative text steganography, the embedding capacity is improved by 16.26∼23.94%. Full article
Show Figures

Figure 1

Back to TopTop