Search Results for author: Kirthi Shankar Sivamani

Found 3 papers, 0 papers with code

Non-Intrusive Detection of Adversarial Deep Learning Attacks via Observer Networks

no code implementations22 Feb 2020 Kirthi Shankar Sivamani, Rajeev Sahay, Aly El Gamal

In this letter, we propose a novel method to detect adversarial inputs, by augmenting the main classification network with multiple binary detectors (observer networks) which take inputs from the hidden layers of the original network (convolutional kernel outputs) and classify the input as clean or adversarial.

Classification General Classification

Feature Losses for Adversarial Robustness

no code implementations10 Dec 2019 Kirthi Shankar Sivamani

We exploit the noisy feature maps by using an additional subnetwork to extract image feature maps and train an auto-encoder on perceptual losses of these feature maps.

Adversarial Robustness Denoising +1

Unsupervised Domain Alignment to Mitigate Low Level Dataset Biases

no code implementations8 Jul 2019 Kirthi Shankar Sivamani

A structured similarity index (SSIM) loss is used to enforce label retention while augmenting the training set.

SSIM

Cannot find the paper you are looking for? You can Submit a new open access paper.