Special Issues
Table of Content

Multimedia Security in Deep Learning

Submission Deadline: 30 September 2024 (closed) View: 784

Guest Editors

Prof. Bin Ma, Qilu University of Technology, China
Prof. Linna Zhou, Beijing University of Posts and Telecommunications, China
Prof. Xiaolong Li, Beijing Jiaotong University, China
Prof. Qi Li, Qilu University of Technology, China
Prof. Xiaoyu Wang, Qilu University of Technology, China

Summary

The special issue titled “Multimedia Security in Deep Learning” serves as a platform to propel research into the inventive applications of deep learning in the realm of Multimedia Security. We extend a global invitation to scholars for the submission of high-quality papers that traverse the cutting-edge intersections of Multimedia Security and Deep Learning. As a part of CSIG Chinese Conference on Media Forensics and Security in 2024, this special issue actively encourages contributions that delve into understanding the impact of Multimedia Security on the performance of deep learning models. Authors are urged to share their insights into innovative methodologies, engage in theoretical discussions, and showcase practical applications within the intersection of Multimedia Security and Deep Learning. Through this collaborative platform, our overarching goal is to stimulate profound cooperation within the global academic community. By doing so, we aim to drive forward state-of-the-art research at the crossroads of color imagery and deep learning. We extend a warm invitation to scholars worldwide to actively participate, contribute to scholarly discussions, and play a pivotal role in advancing knowledge within this interdisciplinary field.


Keywords

Deepfake Generation and Detection
Image Steganography and Steganalysis
Deep Learning Model Security
Image Information Hiding
Image Forensics
Pose Estimation
Semantic Segmentation
Object Detection
Super Resolution
Watermarking and Watermark Attacking
Object Tracking
Image Fusion
Other Related Color Image Processing Fields

Published Papers


  • Open Access

    ARTICLE

    Lip-Audio Modality Fusion for Deep Forgery Video Detection

    Yong Liu, Zhiyu Wang, Shouling Ji, Daofu Gong, Lanxin Cheng, Ruosi Cheng
    CMC-Computers, Materials & Continua, DOI:10.32604/cmc.2024.057859
    (This article belongs to the Special Issue: Multimedia Security in Deep Learning)
    Abstract In response to the problem of traditional methods ignoring audio modality tampering, this study aims to explore an effective deep forgery video detection technique that improves detection precision and reliability by fusing lip images and audio signals. The main method used is lip-audio matching detection technology based on the Siamese neural network, combined with MFCC (Mel Frequency Cepstrum Coefficient) feature extraction of band-pass filters, an improved dual-branch Siamese network structure, and a two-stream network structure design. Firstly, the video stream is preprocessed to extract lip images, and the audio stream is preprocessed to extract MFCC… More >

  • Open Access

    ARTICLE

    IMTNet: Improved Multi-Task Copy-Move Forgery Detection Network with Feature Decoupling and Multi-Feature Pyramid

    Huan Wang, Hong Wang, Zhongyuan Jiang, Qing Qian, Yong Long
    CMC-Computers, Materials & Continua, Vol.80, No.3, pp. 4603-4620, 2024, DOI:10.32604/cmc.2024.053740
    (This article belongs to the Special Issue: Multimedia Security in Deep Learning)
    Abstract Copy-Move Forgery Detection (CMFD) is a technique that is designed to identify image tampering and locate suspicious areas. However, the practicality of the CMFD is impeded by the scarcity of datasets, inadequate quality and quantity, and a narrow range of applicable tasks. These limitations significantly restrict the capacity and applicability of CMFD. To overcome the limitations of existing methods, a novel solution called IMTNet is proposed for CMFD by employing a feature decoupling approach. Firstly, this study formulates the objective task and network relationship as an optimization problem using transfer learning. Furthermore, it thoroughly discusses… More >

  • Open Access

    ARTICLE

    RWNeRF: Robust Watermarking Scheme for Neural Radiance Fields Based on Invertible Neural Networks

    Wenquan Sun, Jia Liu, Weina Dong, Lifeng Chen, Fuqiang Di
    CMC-Computers, Materials & Continua, Vol.80, No.3, pp. 4065-4083, 2024, DOI:10.32604/cmc.2024.053115
    (This article belongs to the Special Issue: Multimedia Security in Deep Learning)
    Abstract As neural radiance fields continue to advance in 3D content representation, the copyright issues surrounding 3D models oriented towards implicit representation become increasingly pressing. In response to this challenge, this paper treats the embedding and extraction of neural radiance field watermarks as inverse problems of image transformations and proposes a scheme for protecting neural radiance field copyrights using invertible neural network watermarking. Leveraging 2D image watermarking technology for 3D scene protection, the scheme embeds watermarks within the training images of neural radiance fields through the forward process in invertible neural networks and extracts them from… More >

  • Open Access

    ARTICLE

    MarkINeRV: A Robust Watermarking Scheme for Neural Representation for Videos Based on Invertible Neural Networks

    Wenquan Sun, Jia Liu, Lifeng Chen, Weina Dong, Fuqiang Di
    CMC-Computers, Materials & Continua, Vol.80, No.3, pp. 4031-4046, 2024, DOI:10.32604/cmc.2024.052745
    (This article belongs to the Special Issue: Multimedia Security in Deep Learning)
    Abstract Recent research advances in implicit neural representation have shown that a wide range of video data distributions are achieved by sharing model weights for Neural Representation for Videos (NeRV). While explicit methods exist for accurately embedding ownership or copyright information in video data, the nascent NeRV framework has yet to address this issue comprehensively. In response, this paper introduces MarkINeRV, a scheme designed to embed watermarking information into video frames using an invertible neural network watermarking approach to protect the copyright of NeRV, which models the embedding and extraction of watermarks as a pair of… More >

  • Open Access

    ARTICLE

    MarkNeRF: Watermarking for Neural Radiance Field

    Lifeng Chen, Jia Liu, Wenquan Sun, Weina Dong, Xiaozhong Pan
    CMC-Computers, Materials & Continua, Vol.80, No.1, pp. 1235-1250, 2024, DOI:10.32604/cmc.2024.051608
    (This article belongs to the Special Issue: Multimedia Security in Deep Learning)
    Abstract This paper presents a novel watermarking scheme designed to address the copyright protection challenges encountered with Neural radiation field (NeRF) models. We employ an embedding network to integrate the watermark into the images within the training set. Then, the NeRF model is utilized for 3D modeling. For copyright verification, a secret image is generated by inputting a confidential viewpoint into NeRF. On this basis, design an extraction network to extract embedded watermark images from confidential viewpoints. In the event of suspicion regarding the unauthorized usage of NeRF in a black-box scenario, the verifier can extract More >

Share Link