Leveraging Generalizability of Image-to-Image Translation for Enhanced Adversarial Defense
This addresses the vulnerability of machine learning models to adversarial attacks, offering a more efficient defense method, though it appears incremental as it builds on previous work.
The paper tackles the problem of adversarial attacks on machine learning models by proposing an improved image-to-image translation-based defense method that incorporates residual blocks to enhance generalizability. The result shows that their model restores classification accuracy from near zero to an average of 72% while defending against diverse attack types with minimal overhead.
In the rapidly evolving field of artificial intelligence, machine learning emerges as a key technology characterized by its vast potential and inherent risks. The stability and reliability of these models are important, as they are frequent targets of security threats. Adversarial attacks, first rigorously defined by Ian Goodfellow et al. in 2013, highlight a critical vulnerability: they can trick machine learning models into making incorrect predictions by applying nearly invisible perturbations to images. Although many studies have focused on constructing sophisticated defensive mechanisms to mitigate such attacks, they often overlook the substantial time and computational costs of training and maintaining these models. Ideally, a defense method should be able to generalize across various, even unseen, adversarial attacks with minimal overhead. Building on our previous work on image-to-image translation-based defenses, this study introduces an improved model that incorporates residual blocks to enhance generalizability. The proposed method requires training only a single model, effectively defends against diverse attack types, and is well-transferable between different target models. Experiments show that our model can restore the classification accuracy from near zero to an average of 72\% while maintaining competitive performance compared to state-of-the-art methods.