Adversarial Vulnerability Bounds for Gaussian Process Classification
원문 초록
Machine learning (ML) classification is increasingly used in safety-critical systems. Protecting ML classifiers from adversarial examples is crucial. We propose that the main threat is that of an attacker perturbing a confidently classified input to produce a confident misclassification. To protect against this we devise an adversarial bound (AB) for a Gaussian process classifier, that holds for the entire input domain, bounding the potential for any future adversarial method to cause such misclassification. This is a formal guarantee of robustness, not just an empirically derived result. We investigate how to configure the classifier to maximise the bound, including the use of a sparse approximation, leading to the method producing a practical, useful and provably robust classifier, which we test using a variety of datasets.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Generative Adversarial Minority Oversampling for Spectral-Spatial Hyperspectral Image Classification
Attention-Based Adaptive Spectral-Spatial Kernel ResNet for Hyperspectral Image Classification
Image and Text fusion for UPMC Food-101 \\using BERT and CNNs
Kidney Level Lupus Nephritis Classification using Uncertainty Guided Bayesian Convolutional Neural Networks
Beyond the Attention: Distinguish the Discriminative and Confusable Features For Fine-grained Image Classification
Orthrus: A Bimodal Learning Architecture for Malware Classification
토론
이 논문과 연결된 포럼 글이 아직 없습니다.