31 citations · 44 across the 11 of their papers we have counts for
11 papers
FLIP: Cross-domain Face Anti-spoofing with Language Guidance
Koushik Srivatsan, Muzammal Naseer, Karthik Nandakumar
Face anti-spoofing (FAS) or presentation attack detection is an essential component of face recognition systems deployed in security-critical applications. Existing FAS methods hav…
FedSIS: Federated Split Learning with Intermediate Representation Sampling for Privacy-preserving Generalized Face Presentation Attack Detection
Naif Alkhunaizi, Koushik Srivatsan, Faris Almalik +2
Lack of generalization to unseen domains/attacks is the Achilles heel of most face presentation attack detection (FacePAD) algorithms. Existing attempts to enhance the generalizabi…
DCTM: Dilated Convolutional Transformer Model for Multimodal Engagement Estimation in Conversation
Vu Ngoc Tu, Van Thong Huynh, Hyung-Jeong Yang +4
Conversational engagement estimation is posed as a regression problem, entailing the identification of the favorable attention and involvement of the participants in the conversati…
Single-branch Network for Multimodal Training
Muhammad Saad Saeed, Shah Nawaz, Muhammad Haris Khan +4
With the rapid growth of social media platforms, users are sharing billions of multimedia posts containing audio, images, and text. Researchers have focused on building autonomous…
Towards Building Text-To-Speech Systems for the Next Billion Users
Gokul Karthik Kumar, Praveen S, Pratyush Kumar +2
Deep learning based text-to-speech (TTS) systems have been evolving rapidly with advances in model architectures, training methodologies, and generalization across speakers and lan…
Self-Ensembling Vision Transformer (SEViT) for Robust Medical Image Classification
Faris Almalik, Mohammad Yaqub, Karthik Nandakumar
Vision Transformers (ViT) are competing to replace Convolutional Neural Networks (CNN) for various computer vision tasks in medical imaging such as classification and segmentation.…
Suppressing Poisoning Attacks on Federated Learning for Medical Imaging
Naif Alkhunaizi, Dmitry Kamzolov, Martin Takáč +1
Collaboration among multiple data-owning entities (e.g., hospitals) can accelerate the training process and yield better machine learning models due to the availability and diversi…
MuCoT: Multilingual Contrastive Training for Question-Answering in Low-resource Languages
Gokul Karthik Kumar, Abhishek Singh Gehlot, Sahal Shaji Mullappilly +1
Accuracy of English-language Question Answering (QA) systems has improved significantly in recent years with the advent of Transformer-based models (e.g., BERT). These models are p…
Efficient Encrypted Inference on Ensembles of Decision Trees
Kanthi Sarpatwar, Karthik Nandakumar, Nalini Ratha +4
Data privacy concerns often prevent the use of cloud-based machine learning services for sensitive personal data. While homomorphic encryption (HE) offers a potential solution by e…
Efficient CNN Building Blocks for Encrypted Data
Nayna Jain, Karthik Nandakumar, Nalini Ratha +2
Machine learning on encrypted data can address the concerns related to privacy and legality of sharing sensitive data with untrustworthy service providers. Fully Homomorphic Encryp…
How to Democratise and Protect AI: Fair and Differentially Private Decentralised Deep Learning
Lingjuan Lyu, Yitong Li, Karthik Nandakumar +2
This paper firstly considers the research problem of fairness in collaborative deep learning, while ensuring privacy. A novel reputation system is proposed through digital tokens a…