Hack The Box: Fooling Deep Learning Abstraction-Based Monitors
원문 초록
Deep learning is a type of machine learning that adapts a deep hierarchy of concepts. Deep learning classifiers link the most basic version of concepts at the input layer to the most abstract version of concepts at the output layer, also known as a class or label. However, once trained over a finite set of classes, some deep learning models do not have the power to say that a given input does not belong to any of the classes and simply cannot be linked. Correctly invalidating the prediction of unrelated classes is a challenging problem that has been tackled in many ways in the literature. Novelty detection gives deep learning the ability to output "do not know" for novel/unseen classes. Still, no attention has been given to the security aspects of novelty detection. In this paper, we consider the case study of abstraction-based novelty detection and show that it is not robust against adversarial samples. Moreover, we show the feasibility of crafting adversarial samples that fool the deep learning classifier and bypass the novelty detection monitoring at the same time. In other words, these monitoring boxes are hackable. We demonstrate that novelty detection itself ends up as an attack surface.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Open-Set Gait Recognition from Sparse mmWave Radar Point Clouds
Killing it with Zero-Shot: Adversarially Robust Novelty Detection
Redefining Normal: A Novel Object-Level Approach for Multi-Object Novelty Detection
Unsupervised Novelty Detection Methods Benchmarking with Wavelet Decomposition
Universal Novelty Detection Through Adaptive Contrastive Learning
Infinite-dimensional Mahalanobis Distance with Applications to Kernelized Novelty Detection
토론
이 논문과 연결된 포럼 글이 아직 없습니다.