Work

Mode: Loss Function for Deep Steganalysis at Low False Positive Rate

Year: 2025

Type: conference-paper

Abstract: Deep steganalysis has been crucial in detecting hidden messages in digital media for nearly a decade. However, its common security evaluation criterion-the probability of error under equal prior-fails to reflect real forensic challenges. In practice, low False Positive (FP) rates matter most but are only adjusted empirically post-training. Standard classifiers, trained with cross-entropy loss, optimize balanced error rates rather than minimizing FPs. We propose a framework that integrates the likelihood ratio test into the loss function to optimize deep classifiers for low FP rates. Our method outperforms standard cross-entropy and other modern approaches, as demonstrated on the BOSSBase dataset across FP rates of 10−3to 10−1in both uncompressed and JPEG domains.

Source: European Signal Processing Conference (EUSIPCO)

DOI: 10.23919/eusipco63237.2025.11226279

Authors: Jan Butora, Patrick Bas

Institutions: Centre National de la Recherche Scientifique, Université de Lille, Centre de Recherche en Informatique, Signal et Automatique de Lille, Centrale Lille Institut

Language: English

Topic: Advanced Steganography and Watermarking Techniques

Subfield: Computer Vision and Pattern Recognition

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

Funder: Agence Nationale de la Recherche

Awards: G1190173965, COntenus Multimedia PROtégés par Machines IntelligenteS