Deep Adversarially-Enhanced k-Nearest Neighbors

by   Ren Wang, et al.
University of Michigan

Recent works have theoretically and empirically shown that deep neural networks (DNNs) have an inherent vulnerability to small perturbations. Applying the Deep k-Nearest Neighbors (DkNN) classifier, we observe a dramatically increasing robustness-accuracy trade-off as the layer goes deeper. In this work, we propose a Deep Adversarially-Enhanced k-Nearest Neighbors (DAEkNN) method which achieves higher robustness than DkNN and mitigates the robustness-accuracy trade-off in deep layers through two key elements. First, DAEkNN is based on an adversarially trained model. Second, DAEkNN makes predictions by leveraging a weighted combination of benign and adversarial training data. Empirically, we find that DAEkNN improves both the robustness and the robustness-accuracy trade-off on MNIST and CIFAR-10 datasets.


page 1

page 2

page 3

page 4


Deep k-Nearest Neighbors: Towards Confident, Interpretable and Robust Deep Learning

Deep neural networks (DNNs) enable innovative applications of machine le...

Adversarial Feature Stacking for Accurate and Robust Predictions

Deep Neural Networks (DNNs) have achieved remarkable performance on a va...

Invariance vs. Robustness of Neural Networks

We study the performance of neural network models on random geometric tr...

Analyzing the Robustness of Nearest Neighbors to Adversarial Examples

Motivated by applications such as autonomous vehicles, test-time attacks...

Architecture Selection via the Trade-off Between Accuracy and Robustness

We provide a general framework for characterizing the trade-off between ...

Knowledge Enhanced Machine Learning Pipeline against Diverse Adversarial Attacks

Despite the great successes achieved by deep neural networks (DNNs), rec...

k-Nearest Neighbors by Means of Sequence to Sequence Deep Neural Networks and Memory Networks

k-Nearest Neighbors is one of the most fundamental but effective classif...

Code Repositories


Deep Adversarially-Enhanced k-Nearest Neighbors

view repo

Please sign up or login with your details

Forgot password? Click here to reset