paper-with-me

Papers

Towards Dependable Deep Convolutional Neural Networks (CNNs) with Out-distribution Learning

2018-04-24 · Mahdieh Abbasi, Arezoo Rajabi, Christian Gagné, Rakesh B. Bobba

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%).

📄 PDF Abstract BibTeX arXiv:1804.08794

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Cogradient Descent for Dependable Learning

2021-06-20 · Runqi Wang, Baochang Zhang, Li'an Zhuo, Qixiang Ye 외

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 Pruning

Enhancing Diabetic Retinopathy Detection with CNN-Based Models: A Comparative Study of UNET and Stacked UNET Architectures

2024-11-02 · Ameya Uppina, S Navaneetha Krishnan, Talluri Krishna Sai Teja, Nikhil N Iyer 외

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 Detection

Architecting Dependable Learning-enabled Autonomous Systems: A Survey

2019-02-27 · Chih-Hong Cheng, Dhiraj Gulati, Rongjie Yan

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…

Survey

Hybrid Convolutional Neural Networks with Reliability Guarantee

2024-05-08 · Hans Dermot Doran, Suzana Veljanovska

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

2024-12-28 · Shilong Wang, Jianchun Liu, Hongli Xu, Chunming Qiao 외

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