A Training-Free Defense Framework for Robust Learned Image Compression
This addresses robustness issues in image compression for applications like storage and transmission, but it is incremental as it builds on existing models without fundamental changes.
The paper tackles the vulnerability of learned image compression models to adversarial attacks by proposing a training-free defense technique using random input transforms, which preserves rate-distortion performance on clean images without requiring model modifications.
We study the robustness of learned image compression models against adversarial attacks and present a training-free defense technique based on simple image transform functions. Recent learned image compression models are vulnerable to adversarial attacks that result in poor compression rate, low reconstruction quality, or weird artifacts. To address the limitations, we propose a simple but effective two-way compression algorithm with random input transforms, which is conveniently applicable to existing image compression models. Unlike the naïve approaches, our approach preserves the original rate-distortion performance of the models on clean images. Moreover, the proposed algorithm requires no additional training or modification of existing models, making it more practical. We demonstrate the effectiveness of the proposed techniques through extensive experiments under multiple compression models, evaluation metrics, and attack scenarios.