Towards Dependable Deep Convolutional Neural Networks (CNNs) with Out-distribution Learning
Detection and rejection of adversarial examples in security sensitive and safety-critical systems using deep CNNs is essential. In this paper, we propose an approach to augment CNNs with out-distribution learning in order to reduce misclassification rate by rejecting adversarial examples. We empirically show that our augmented CNNs can either reject or classify correctly most adversarial examples generated using well-known methods ( >95% for MNIST and >75% for CIFAR-10 on average). Furthermore, we achieve this without requiring to train using any specific type of adversarial examples and without sacrificing the accuracy of models on clean samples significantly (< 4%).
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Cogradient Descent for Dependable Learning
Conventional gradient descent methods compute the gradients for multiple variables through the partial derivative. Treating the coupled variables independently while ignoring the interaction, however, leads to an insuffi…
Image InpaintingImage ReconstructionNetwork PruningEnhancing Diabetic Retinopathy Detection with CNN-Based Models: A Comparative Study of UNET and Stacked UNET Architectures
Diabetic Retinopathy DR is a severe complication of diabetes. Damaged or abnormal blood vessels can cause loss of vision. The need for massive screening of a large population of diabetic patients has generated an interes…
Diabetic Retinopathy DetectionArchitecting Dependable Learning-enabled Autonomous Systems: A Survey
We provide a summary over architectural approaches that can be used to construct dependable learning-enabled autonomous systems, with a focus on automated driving. We consider three technology pillars for architecting de…
SurveyHybrid Convolutional Neural Networks with Reliability Guarantee
Making AI safe and dependable requires the generation of dependable models and dependable execution of those models. We propose redundant execution as a well-known technique that can be used to ensure reliable execution …
A Robust Federated Learning Framework for Undependable Devices at Scale
In a federated learning (FL) system, many devices, such as smartphones, are often undependable (e.g., frequently disconnected from WiFi) during training. Existing FL frameworks always assume a dependable environment and …
Federated Learning