Steganographic Capacity of Transformer Models

Lei Zhang, Dong Li, Olha Jurečková and Mark Stamp ()
Additional contact information
Lei Zhang: San Jose State University
Dong Li: Shanghai AI Laboratory
Olha Jurečková: Czech Technical University in Prague
Mark Stamp: San Jose State University

A chapter in Machine Learning, Deep Learning and AI for Cybersecurity, 2025, pp 507-526 from Springer

Abstract: Abstract As machine learning and deep learning models become ubiquitous, it is inevitable that there will be attempts to exploit such models in various attack scenarios. For example, in a steganographic-based attack, information could be hidden in a learning model, which might then be used to distribute malware, or for other malicious purposes. In this research, our focus is on the steganographic capacity a Transformer model, but for comparison we also consider a Multilayer Perceptron (MLP) and Convolutional Neural Network (CNN). All three models are trained on a challenging malware classification problem, and for each models, we determine the number of low-order bits of the trained parameters that can be altered without significantly affecting the classification accuracy. We find that the steganographic capacity of the learning models tested is surprisingly high, and that in each case, there is a clear threshold after which model performance rapidly degrades. Due to its large number of weights, we find that the Transformer model has a steganographic capacity that is orders of magnitude larger than that of either the MLP or CNN models.

Date: 2025
References: Add references at CitEc
Citations: View citations in EconPapers (2)

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:sprchp:978-3-031-83157-7_18

Ordering information: This item can be ordered from
http://www.springer.com/9783031831577

DOI: 10.1007/978-3-031-83157-7_18

Access Statistics for this chapter

More chapters in Springer Books from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().