Simple black-box universal adversarial attacks on medical image classification based on deep neural networks
원문 초록
Universal adversarial attacks, which hinder most deep neural network (DNN) tasks using only a small single perturbation called a universal adversarial perturbation (UAP), is a realistic security threat to the practical application of a DNN. In particular, such attacks cause serious problems in medical imaging. Given that computer-based systems are generally operated under a black-box condition in which only queries on inputs are allowed and outputs are accessible, the impact of UAPs seems to be limited because well-used algorithms for generating UAPs are limited to a white-box condition in which adversaries can access the model weights and loss gradients. Nevertheless, we demonstrate that UAPs are easily generatable using a relatively small dataset under black-box conditions. In particular, we propose a method for generating UAPs using a simple hill-climbing search based only on DNN outputs and demonstrate the validity of the proposed method using representative DNN-based medical image classifications. Black-box UAPs can be used to conduct both non-targeted and targeted attacks. Overall, the black-box UAPs showed high attack success rates (40% to 90%), although some of them had relatively low success rates because the method only utilizes limited information to generate UAPs. The vulnerability of black-box UAPs was observed in several model architectures. The results indicate that adversaries can also generate UAPs through a simple procedure under the black-box condition to foil or control DNN-based medical image diagnoses, and that UAPs are a more realistic security threat.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Deep Modeling and Optimization of Medical Image Classification
Advancements in Medical Image Classification through Fine-Tuning Natural Domain Foundation Models
Learning Concept-Driven Logical Rules for Interpretable and Generalizable Medical Image Classification
Improving Generalizability of Kolmogorov-Arnold Networks via Error-Correcting Output Codes
V-EfficientNets: Vector-Valued Efficiently Scaled Convolutional Neural Network Models
FedGSCA: Medical Federated Learning with Global Sample Selector and Client Adaptive Adjuster under Label Noise
토론
이 논문과 연결된 포럼 글이 아직 없습니다.