154 citations · 1.1k across the 66 of their papers we have counts for
5 papers · 1 filter
Not all Failure Modes are Created Equal: Training Deep Neural Networks for Explicable (Mis)Classification
Alberto Olmo, Sailik Sengupta, Subbarao Kambhampati
Deep Neural Networks are often brittle on image classification tasks and known to misclassify inputs. While these misclassifications may be inevitable, all failure modes cannot be…
Imperfect ImaGANation: Implications of GANs Exacerbating Biases on Facial Data Augmentation and Snapchat Selfie Lenses
Niharika Jain, Alberto Olmo, Sailik Sengupta +2
In this paper, we show that popular Generative Adversarial Networks (GANs) exacerbate biases along the axes of gender and skin tone when given a skewed distribution of face-shots.…
Imagining an Engineer: On GAN-Based Data Augmentation Perpetuating Biases
Niharika Jain, Lydia Manikonda, Alberto Olmo Hernandez +2
The use of synthetic data generated by Generative Adversarial Networks (GANs) has become quite a popular method to do data augmentation for many applications. While practitioners c…
MTDeep: Boosting the Security of Deep Neural Nets Against Adversarial Attacks with Moving Target Defense
Sailik Sengupta, Tathagata Chakraborti, Subbarao Kambhampati
Present attack methods can make state-of-the-art classification systems based on deep neural networks misclassify every adversarially modified test example. The design of general d…
ET-LDA: Joint Topic Modeling For Aligning, Analyzing and Sensemaking of Public Events and Their Twitter Feeds
Yuheng Hu, Ajita John, Fei Wang +2
Social media channels such as Twitter have emerged as popular platforms for crowds to respond to public events such as speeches, sports and debates. While this promises tremendous…