Selection of Robust and Relevant Features for 3-D Steganalysis

Research output: Contribution to journalArticlepeer-review


While 3-D steganography and digital watermarking represent methods for embedding information into 3-D objects, 3-D steganalysis aims to find the hidden information. Previous research studies have shown that by estimating the parameters modelling the statistics of 3-D features and feeding them into a classifier we can identify whether a 3-D object carries secret information. For training the steganalyser such features are
extracted from cover and stego pairs, representing the original 3-D objects and those carrying hidden information. However, in practical applications, the steganalyzer would have to distinguish stego-objects from cover-objects, which most likely have not been used during the training. This represents a significant challenge for existing steganalyzers, raising a challenge known as the Cover Source Mismatch (CSM) problem, which is due to the significant limitation of their generalization ability. This paper proposes a novel feature selection algorithm taking into account both feature robustness and relevance in order to mitigate the CSM problem in 3-D steganalysis. In the context of the proposed methodology, new shapes are generated by distorting those used in the training. Then a subset of features is selected from a larger given set, by assessing their effectiveness in separating cover objects from stego-objects among the generated sets of objects. Two different measures are used for selecting the appropriate features: Pearson Correlation Coefficient (PCC) and the Mutual Information Criterion (MIC).
Original languageEnglish
Pages (from-to)1989-2001
Number of pages13
JournalIEEE Transactions on Cybernetics
Issue number5
Publication statusPublished - 14 Dec 2018

Bibliographical note

© 2018 IEEE.


  • 3-D steganalysis
  • Data mining
  • Feature extraction
  • Machine learning
  • Machine learning algorithms
  • Robustness
  • Shape
  • Training
  • cover source mismatch
  • feature selection

Cite this