Recommended articles

更多

Automated vulnerability discovery method for 5G core network protocol

With the widespread development of fifth-generation (5G) mobile communication technology, concerns regarding 5G network security have also increased.Blackbox fuzzing is a commonly used method for automated vulnerability discovery in software security.However, applying dynamic approaches like fuzzing to discover vulnerabilities in the complex design of 5G core network protocols poses challenges such as low efficiency, poor versatility, and lack of scalability.Therefore, a novel static method to examine the open-source solution of the 5G core network was proposed.Through this method, a series of memory leak security issues caused by improper variable life cycle management were identified, which can lead to denial-of-service attacks on the 5G core network.To summarize these weaknesses, a general vulnerability model and an automated vulnerability discovery method called HoI were presented, which utilized hybrid analysis based on control and data flow.By successfully discovering five zero-day bugs in Open5GS, an open-source solution for the 5G core network, vulnerabilities that cover practical application scenarios of multiple interface protocols in the 5G core network were identified.These vulnerabilities have wide-ranging impact, are highly detrimental, and can be easily exploited.They have been reported to the vendor and assigned four Common Vulnerabilities and Exposures (CVE) numbers, demonstrating the effectiveness of this automated vulnerability discovery method.

> Papers

Peixiang WU, Zhilong ZHANG, Libo CHEN, Yijun WANG, Zhi XUE

Automated vulnerability discovery method for 5G core network protocol
  • Latest Articles
  • Online First
  • Archive
更多
Volume 12 期 4，2026 2026年第12卷第4期

    专题导读 AI导读

      
    9
    |
    18
    |
    0
    <HTML>
    <L-PDF><WORD><XML><Meta-XML>
    <引用本文> <批量引用> 171445394 false
    更新时间：2026-09-11

  • Special Issue\: Information Hiding and Analysis

    Liu Minglin, Wang Yuqi, Guo Suxian, Sun Junqi, Zhong Zhichao, Luo Xiangyang, Luo Weiqi

    DOI：10.11959/j.issn.2096-109x.AQ26102
    摘要：Hiding image within image is an emerging image steganography technique that aims to hide a secret image within a cover image and enable covert transmission while preserving the visual appearance of the stego image as much as possible. Existing methods usually employ end-to-end neural networks to perform secret image embedding and extraction, focusing mainly on network architecture design while making insufficient use of mature secure embedding mechanisms from traditional steganography. As a result, there remains room for improvement in the steganographic security of stego images. To address this issue, a decoupled image steganography framework based on pyramid vision transformer (PVT) encoding, binary feature compression, traditional steganographic embedding, and Swin Transformer for image restoration (SwinIR) reconstruction was proposed. Specifically, the framework first used a PVT encoder to extract and compress features from the secret image, and then converted them into a binary bitstream through a binarization module. The binary bitstream was subsequently embedded into the cover image using space-time code (STC) from traditional color image steganography to generate the stego image. In the extraction stage, the binary bitstream was recovered through STC decoding, and the secret image was reconstructed using SwinIR based on a window-attention mechanism. Unlike existing methods for hiding image within image that rely on neural embedding networks, the proposed method replaced the neural embedding network with STC, enabling deep feature representation to be combined with the distortion modeling mechanism of traditional color image steganography, thereby reducing the detectability of stego images. Experimental results show that the proposed method can effectively reconstruct the secret image while maintaining high visual quality between the cover and stego images, and shows a certain relative security improvement against color spatial rich model (Color-SRM) and CovNet steganalyzers.  
    关键词：image steganography;hiding image within image;binary feature compression;super resolution reconstruction   
    80
    |
    34
    |
    0
    <HTML>
    <L-PDF><WORD><XML><Meta-XML>
    <引用本文> <批量引用> 171445194 false
    更新时间：2026-09-11

    Guo Bobiao, Yang Xiaohui, Ping Ping

    DOI：10.11959/j.issn.2096-109x.AQ26053
    摘要：Image steganography plays a vital role in protecting private images in covert communication and secure cloud storage. Unlike one-time covert communication, cloud-based secure image storage requires supporting multiple accesses to private images. Existing steganography methods for lossless reconstruction of private images can prevent distortion accumulation over multiple embedding and reconstruction cycles. However, they lack sufficient robustness and struggle to reconstruct perceptually recognizable private images in lossy environments. To address this, a method was proposed that achieves lossless reconstruction of private images in lossless conditions while enabling perceptually recognizable reconstruction under lossy conditions. First, a nested quantization index modulation with dither compensation (DC-NQIM) algorithm was proposed, which doubles the embedding capacity of quantization index modulation. Subsequently, by optimizing the carrier stability and the synergistic matching relationship between the bit-planes of privacy images and the nested modulation levels, it was ensured that the bit-planes contributing more to the visual quality of the image were assigned to the modulation levels with better stability. Finally, a local structure-aware adaptive privacy images error correction algorithm was introduced to avoid local artifacts caused by bit-plane error accumulation. Experimental results show that the proposed method achieves an infinite PSNR for reconstructing privacy images under lossless conditions, thereby supporting repeated access to privacy images; under lossy conditions, it can reconstruct perceptually recognizable privacy images with a PSNR close to 30 dB, making it suitable for lossy cloud-based privacy images protection scenarios.  
    关键词：information hiding;privacy protection;image-in-image;quantization index modulation   
    59
    |
    41
    |
    0
    <HTML>
    <L-PDF><WORD><XML><Meta-XML>
    <引用本文> <批量引用> 171445192 false
    更新时间：2026-09-11

    Ren Fang, Wang Jing, Zhang Xing, Yang Tengfei

    DOI：10.11959/j.issn.2096-109x.AQ26098
    摘要：Reversible data hiding in encrypted images (RDHEI), which can simultaneously protect the cover image and private data, has been widely studied in recent years. To address the issues of limited embedding capacity due to underutilization of high bit-planes redundancy and inaccurate prediction of complex image regions, a novel RDHEI method based on combined prediction optimization, hierarchical block compression, and context-based adaptive binary arithmetic coding (CABAC) was proposed. Firstly, by integrating the combined predictor and prediction error modification (PEM) strategy, the accuracy of prediction in complex regions and compression efficiency were effectively improved. Secondly, a quadtree-based adaptive hierarchical block compression strategy was designed to replace fixed partitioning, allowing for more flexible redundancy minimization. Finally, CABAC was applied to further reduce auxiliary information. This approach effectively increases embedding capacity and ensures lossless image recovery. Experimental results show that the proposed method outperforms existing mainstream methods in terms of embedding rate. On the three public datasets BOSSbase, BOWS-2 and UCID, the average embedding rates of the proposed method are 4.324 5 bit/pixel, 4.232 7 bit/pixel and 3.575 2 bit/pixel, respectively, which correspond to improvements of 3.63%, 3.59% and 2.38% over existing mainstream methods.  
    关键词：reversible data hiding;encrypted images;combined prediction optimization;hierarchical block compression   
    24
    |
    27
    |
    0
    <HTML>
    <L-PDF><WORD><XML><Meta-XML>
    <引用本文> <批量引用> 171445190 false
    更新时间：2026-09-11

    Wang Jianhang, Di Fuqiang, Zhu Shuaishuai, Liu Lang

    DOI：10.11959/j.issn.2096-109x.AQ26094
    摘要：Neural style transfer has been widely used in digital creation, cultural heritage restoration, and other fields. However, the copyright attribution and traceability of generated content urgently need to be addressed. Existing watermarking techniques suffer from problems such as weak fusion between style and watermark, insufficient robustness, and degraded visual quality, and are not well adapted to the generation characteristics of latent diffusion models. To solve these issues, a neural style transfer watermarking algorithm based on StyleID for copyright protection and traceability of style-transferred generated content was proposed. The algorithm dynamically captures the key fusion regions of content and style features through an attention mechanism, generates a fused latent vector after style injection, and completes watermark embedding at the decoder stage of the latent diffusion model, realizing deep binding between the watermark and the style transfer process. Experimental results show that the proposed algorithm maintains high visual quality of style-transferred images, while the extraction accuracy of the watermark against common attacks such as cropping, blurring, and JPEG compression is above 98%. It can effectively support copyright protection and traceability of style-transferred generated content, providing technical support for the legitimate application of generative AI content.  
    关键词：style transfer;digital watermarking;latent diffusion models;content tracing;copyright protection   
    23
    |
    47
    |
    0
    <HTML>
    <L-PDF><WORD><XML><Meta-XML>
    <引用本文> <批量引用> 171445047 false
    更新时间：2026-09-11
查看更多

Quick Entry

  • Author login
  • Peer Review
  • Editorial Office

               

Copyright Information

Bimonthly, started in 2015
Authorized by:Ministry of Industry and Information Technology of the People's Republic of China
Sponsored by:Posts and Telecommunications Press
Co-sponsored by:Xidian University, Beihang University, Huazhong University of Science and Technology, Zhejiang University
Edited by:Editorial Board of Chinese Journal of Network and Information Security
Editor-in-Chief:FANG Bin-xing
Executive Editor-in-Chief:LI Feng-hua
Director:Xing Jianchun
Address:F2, Beiyang Chenguang Building, Shunbatiao No.1 Courtyard, Fengtai District, Beijing, China
Tel:010-53879136/53879078
Fax:+86-81055464
ISSN 2096-109X(print)

ISSN 2097-5554（online）
CN 10-1366/TP

Copyright Information
0