DEM: A Method for Certifying Deep Neural Network Classifier Outputs in Aerospace
Software development in the aerospace domain requires adhering to strict, high-quality standards. While there exist regulatory guidelines for commercial software in this domain (e.g., ARP-4754 and DO-178), these do not apply to software with deep neural network (DNN) components. Consequently, it is unclear how to allow aerospace systems to benefit from the deep learning revolution. Our work here seeks to address this challenge with a novel, output-centric approach for DNN certification. Our method employs statistical verification techniques, and has the key advantage of being able to flag specific inputs for which the DNN's output may be unreliable - so that they may be later inspected by a human expert. To achieve this, our method conducts a statistical analysis of the DNN's predictions for other, nearby inputs, in order to detect inconsistencies. This is in contrast to existing techniques, which typically attempt to certify the entire DNN, as opposed to individual outputs. Our method uses the DNN as a black-box, and makes no assumptions about its topology. We hope that this work constitutes another step towards integrating DNNs in safety-critical applications - especially in the aerospace domain, where high standards of quality and reliability are crucial.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Diagnosis of aerospace structure defects by a HPC implemented soft computing algorithm
This study concerns with the diagnosis of aerospace structure defects by applying a HPC parallel implementation of a novel learning algorithm, named U-BRAIN. The Soft Computing approach allows advanced multi-parameter da…
Self-Certifying Classification by Linearized Deep Assignment
We propose a novel class of deep stochastic predictors for classifying metric data on graphs within the PAC-Bayes risk certification paradigm. Classifiers are realized as linearly parametrized deep assignment flows with …
ClassificationCertifying Adapters: Enabling and Enhancing the Certification of Classifier Adversarial Robustness
Randomized smoothing has become a leading method for achieving certified robustness in deep classifiers against l_{p}-norm adversarial perturbations. Current approaches for achieving certified robustness, such as data au…
Adversarial RobustnessData AugmentationCertifying Robustness of Graph Laplacian Based Semi-Supervised Learning
Graph Laplacian (GL)-based semi-supervised learning is one of the most used approaches for classifying nodes in a graph. Understanding and certifying the adversarial robustness of machine learning (ML) algorithms have at…
Adversarial RobustnessAlmost Tight L0-norm Certified Robustness of Top-k Predictions against Adversarial Perturbations
Top-k predictions are used in many real-world applications such as machine learning as a service, recommender systems, and web searches. $\ell_0$-norm adversarial perturbation characterizes an attack that arbitrarily mod…
Recommendation Systems