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

2018/04/24 by Mahdieh Abbasi, Arezoo Rajabi, Abbasi, Mahdieh +5
Computer Science · #Advanced Malware Detection Techniques #Adversarial Robustness in Machine Learning #Anomaly Detection Techniques and Applications #Cryptography and Security (cs.CR) #FOS: Computer and information sciences #Machine Learning (cs.LG)

paper · pdf · doi:10.48550/arxiv.1804.08794

openalex publication_date 2018/04/24 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

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%).

Related

• Controlling Over-generalization and its Effect on Adversarial Examples Generation and Detection
• Out-distribution training confers robustness to deep neural networks
• Less is More: Culling the Training Set to Improve Robustness of Deep Neural Networks
• HyperNetworks with statistical filtering for defending adversarial examples
• Adversarial Examples Detection in Deep Networks with Convolutional Filter Statistics