6 papers
Mimicking Human Visual Development for Learning Robust Image Representations
Ankita Raj, Kaashika Prajaapat, Tapan Kumar Gandhi +1
The human visual system is remarkably adept at adapting to changes in the input distribution; a capability modern convolutional neural networks (CNNs) still struggle to match. Draw…
Backdoor Attacks on Open Vocabulary Object Detectors via Multi-Modal Prompt Tuning
Ankita Raj, Chetan Arora
Open-vocabulary object detectors (OVODs) unify vision and language to detect arbitrary object categories based on text prompts, enabling strong zero-shot generalization to novel co…
Identifying Physically Realizable Triggers for Backdoored Face Recognition Networks
Ankita Raj, Ambar Pal, Chetan Arora
Backdoor attacks embed a hidden functionality into deep neural networks, causing the network to display anomalous behavior when activated by a predetermined pattern in the input Tr…
Assessing Risk of Stealing Proprietary Models for Medical Imaging Tasks
Ankita Raj, Harsh Swaika, Deepankar Varma +1
The success of deep learning in medical imaging applications has led several companies to deploy proprietary models in diagnostic workflows, offering monetized services. Even thoug…
Examining the Threat Landscape: Foundation Models and Model Stealing
Ankita Raj, Deepankar Varma, Chetan Arora
Foundation models (FMs) for computer vision learn rich and robust representations, enabling their adaptation to task/domain-specific deployments with little to no fine-tuning. Howe…
Analysis and Synthesis Prior Greedy Algorithms for Non-linear Sparse Recovery
Kavya Gupta, Ankita Raj, Angshul Majumdar
In this work we address the problem of recovering sparse solutions to non linear inverse problems. We look at two variants of the basic problem, the synthesis prior problem when th…