FACL-Attack: Frequency-Aware Contrastive Learning for Transferable Adversarial Attacks
This work addresses security vulnerabilities in deep neural networks for real-world applications where target details are unknown, offering an incremental improvement over existing generative model-based attacks.
The paper tackles the challenge of generating transferable adversarial attacks in strict black-box settings by proposing a frequency-aware contrastive learning method, achieving strong transferability across domains and models while maintaining inference efficiency.
Deep neural networks are known to be vulnerable to security risks due to the inherent transferable nature of adversarial examples. Despite the success of recent generative model-based attacks demonstrating strong transferability, it still remains a challenge to design an efficient attack strategy in a real-world strict black-box setting, where both the target domain and model architectures are unknown. In this paper, we seek to explore a feature contrastive approach in the frequency domain to generate adversarial examples that are robust in both cross-domain and cross-model settings. With that goal in mind, we propose two modules that are only employed during the training phase: a Frequency-Aware Domain Randomization (FADR) module to randomize domain-variant low- and high-range frequency components and a Frequency-Augmented Contrastive Learning (FACL) module to effectively separate domain-invariant mid-frequency features of clean and perturbed image. We demonstrate strong transferability of our generated adversarial perturbations through extensive cross-domain and cross-model experiments, while keeping the inference time complexity.