Reversing Skin Cancer Adversarial Examples by Multiscale Diffusive and Denoising Aggregation Mechanism
This work addresses the critical problem of adversarial attacks in medical imaging for skin cancer diagnosis, offering a resource-efficient solution, though it is incremental as it builds on existing defense mechanisms.
The paper tackles the vulnerability of deep learning-based skin cancer diagnosis models to adversarial attacks by proposing a defense framework that reverses adversarial perturbations through multiscale diffusion and denoising aggregation. The method was evaluated on the ISIC 2019 dataset and significantly outperformed state-of-the-art defenses in protecting skin cancer models.
Reliable skin cancer diagnosis models play an essential role in early screening and medical intervention. Prevailing computer-aided skin cancer classification systems employ deep learning approaches. However, recent studies reveal their extreme vulnerability to adversarial attacks -- often imperceptible perturbations to significantly reduce the performances of skin cancer diagnosis models. To mitigate these threats, this work presents a simple, effective, and resource-efficient defense framework by reverse engineering adversarial perturbations in skin cancer images. Specifically, a multiscale image pyramid is first established to better preserve discriminative structures in the medical imaging domain. To neutralize adversarial effects, skin images at different scales are then progressively diffused by injecting isotropic Gaussian noises to move the adversarial examples to the clean image manifold. Crucially, to further reverse adversarial noises and suppress redundant injected noises, a novel multiscale denoising mechanism is carefully designed that aggregates image information from neighboring scales. We evaluated the defensive effectiveness of our method on ISIC 2019, a largest skin cancer multiclass classification dataset. Experimental results demonstrate that the proposed method can successfully reverse adversarial perturbations from different attacks and significantly outperform some state-of-the-art methods in defending skin cancer diagnosis models.