no code implementations • 2 Mar 2023 • Pratinav Seth, Akshat Bhandari, Kumud Lakara
This is especially the case for computer vision 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.
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.
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.
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.