Analyzing Effects of Fake Training Data on the Performance of Deep Learning Systems

no code implementations • 2 Mar 2023 • Pratinav Seth, Akshat Bhandari, Kumud Lakara

This is especially the case for computer vision models.

Disentangled Uncertainty and Out of Distribution Detection in Medical Generative Models

no code implementations • 11 Nov 2022 • Kumud Lakara, Matias Valdenegro-Toro

Trusting the predictions of deep learning models in safety critical settings such as the medical domain is still not a viable option.

Image-to-Image Translation Out-of-Distribution Detection +2

Design and Analysis of Novel Bit-flip Attacks and Defense Strategies for DNNs

1 code implementation • IEEE Conference on Dependable and Secure Computing (DSC) 2022 • Yash Khare, Kumud Lakara, Maruthi S Inukonda, Sparsh Mittal, Mahesh Chandra, Arvind Kaushik

In this paper, we present novel bit-flip attack (BFA) algorithms for DNNs, along with techniques for defending against the attack.

Evaluating Predictive Uncertainty and Robustness to Distributional Shift Using Real World Data

no code implementations • 8 Nov 2021 • Kumud Lakara, Akshat Bhandari, Pratinav Seth, Ujjwal Verma

The magnitude of a model's performance is proportional to this shift in the distribution of the dataset.

BERT based Transformers lead the way in Extraction of Health Information from Social Media

1 code implementation • NAACL (SMM4H) 2021 • Sidharth R, Abhiraj Tiwari, Parthivi Choubey, Saisha Kashyap, Sahil Khose, Kumud Lakara, Nishesh Singh, Ujjwal Verma

This paper describes our submissions for the Social Media Mining for Health (SMM4H)2021 shared tasks.

Binary Classification Classification +2