Detection of Classifier Inconsistencies in Image Steganalysis

被引:8
|
作者
Lerch-Hostalot, Daniel [1 ]
Megias, David [1 ]
机构
[1] UOC, Internet Interdisciplinary Inst IN3, CYBERCAT Ctr Cybersecur Res Catalonia, Barcelona, Spain
关键词
Steganalysis; Cover Source Mismatch; Machine Learning;
D O I
10.1145/3335203.3335738
中图分类号
TP301 [理论、方法];
学科分类号
081202 ;
摘要
In this paper, a methodology to detect inconsistencies in classification-based image steganalysis is presented. The proposed approach uses two classifiers: the usual one, trained with a set formed by cover and stego images, and a second classifier trained with the set obtained after embedding additional random messages into the original training set. When the decisions of these two classifiers are not consistent, we know that the prediction is not reliable. The number of inconsistencies in the predictions of a testing set may indicate that the classifier is not performing correctly in the testing scenario. This occurs, for example, in case of cover source mismatch, or when we are trying to detect a steganographic method that the classifier is no capable of modelling accurately. We also show how the number of inconsistencies can be used to predict the reliability of the classifier (classification errors).
引用
收藏
页码:222 / 229
页数:8
相关论文
共 50 条
  • [1] Single-image steganalysis in real-world scenarios based on classifier inconsistency detection
    Lerch-Hostalot, Daniel
    Megias, David
    19TH INTERNATIONAL CONFERENCE ON AVAILABILITY, RELIABILITY, AND SECURITY, ARES 2024, 2024,
  • [2] Real-world actor-based image steganalysis via classifier inconsistency detection
    Lerch-Hostalot, Daniel
    Megias, David
    18TH INTERNATIONAL CONFERENCE ON AVAILABILITY, RELIABILITY & SECURITY, ARES 2023, 2023,
  • [3] BLOCK-BASED IMAGE STEGANALYSIS FOR A MULTI-CLASSIFIER
    Cho, Seongho
    Wang, Jingwei
    Kuo, C. -C. Jay
    Cha, Byung-Ho
    2010 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO (ICME 2010), 2010, : 1457 - 1462
  • [4] Steganalysis aided by fragile detection of image manipulations
    Wang, Ping
    Liu, Fenlin
    Yang, Chunfang
    Luo, Xiangyang
    MULTIMEDIA TOOLS AND APPLICATIONS, 2019, 78 (16) : 23309 - 23328
  • [5] Noise features for image tampering detection and steganalysis
    Gou, Hongmei
    Swaminathan, Ashwin
    Wu, Min
    2007 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, VOLS 1-7, 2007, : 2893 - 2896
  • [6] Steganalysis aided by fragile detection of image manipulations
    Ping Wang
    Fenlin Liu
    Chunfang Yang
    Xiangyang Luo
    Multimedia Tools and Applications, 2019, 78 : 23309 - 23328
  • [7] Image Modelling: A Feature Detection Approach for Steganalysis
    Rani, Anuj
    Kumar, Manoj
    Goel, Payel
    ADVANCES IN COMPUTING AND DATA SCIENCES, ICACDS 2016, 2017, 721 : 140 - 148
  • [8] Multi-class JPEG Image Steganalysis by Ensemble Linear SVM Classifier
    Zhu, Jie
    Guan, Qingxiao
    Zhao, Xianfeng
    DIGITAL-FORENSICS AND WATERMARKING, IWDW 2014, 2015, 9023 : 470 - 484
  • [9] Image edge detection with fuzzy classifier
    Liang, LR
    Basallo, E
    Looney, CG
    COMPUTER APPLICATIONS IN INDUSTRY AND ENGINEERING, 2001, : 279 - 282
  • [10] Compressive Sensing Based Feature Residual for Image Steganalysis Detection
    Zhao, Huimin
    Pei, Zhenzhen
    Cai, Zhengye
    Dai, Qingyun
    Wei, Wenguo
    Ren, Jingchang
    2017 IEEE INTERNATIONAL CONFERENCE ON INTERNET OF THINGS (ITHINGS) AND IEEE GREEN COMPUTING AND COMMUNICATIONS (GREENCOM) AND IEEE CYBER, PHYSICAL AND SOCIAL COMPUTING (CPSCOM) AND IEEE SMART DATA (SMARTDATA), 2017, : 1096 - 1100