FGAS: Fixed Decoder Network-Based Audio Steganography with Adversarial Perturbation Generation

TL;DR

FGAS introduces a fixed decoder network and adversarial perturbation technique to enhance audio steganography's quality, robustness, and anti-steganalysis performance, addressing computational and security challenges of prior methods.

Contribution

The paper pioneers a fixed decoder-based audio steganography method with adversarial perturbations, significantly improving quality and security over existing encoder-decoder approaches.

Findings

Achieves over 10 dB PSNR gain compared to state-of-the-art methods.

Demonstrates robustness against common audio processing attacks.

Maintains strong anti-steganalysis performance with only 2% higher error rate.

Abstract

The rapid development of Artificial Intelligence Generated Content (AIGC) has made high-fidelity generated audio widely available across the Internet, driving the advancement of audio steganography. Benefiting from advances in deep learning, current audio steganography schemes are mainly based on encoder-decoder network architectures. While these methods guarantee a certain level of perceptual quality for stego audio, they typically face high computational cost and long implementation time, as well as poor anti-steganalysis performance. To address the aforementioned issues, we pioneer a Fixed Decoder Network-Based Audio Steganography with Adversarial Perturbation Generation (FGAS). Adversarial perturbations carrying a secret message are embedded into the cover audio to generate stego audio. The receiver only needs to share the structure and key of the fixed decoder network to accurately extract the secret message from the stego audio. In FGAS, we propose an Audio Adversarial Perturbation Generation (A2PG) strategy with an optional robust extension and design a lightweight fixed decoder. The fixed decoder guarantees reliable extraction of the hidden message, while adversarial perturbations are optimized to keep the stego audio perceptually and statistically close to the cover audio, thereby improving anti-steganalysis performance. The experimental results show that FGAS significantly improves stego audio quality, achieving an average PSNR gain of over 10 dB compared to SOTA methods. Furthermore, FGAS demonstrates strong robustness against common audio processing attacks. Moreover, FGAS exhibits superior anti-steganalysis performance across different relative payloads; under high-capacity embedding, it achieves a classification error rate about 2% higher, indicating stronger anti-steganalysis performance than current SOTA methods.