activity
20222025
most citedAdversarial Pixel Restoration as a Pretext Task for Transferable Perturbations

2 citations · 2 across the 4 of their papers we have counts for

collaborators

5 papers

cs.CV2025

Hierarchical Self-Supervised Adversarial Training for Robust Vision Models in Histopathology

Hashmat Shadab Malik, Shahina Kunhimon, Muzammal Naseer +2

Adversarial attacks pose significant challenges for vision models in critical fields like healthcare, where reliability is essential. Although adversarial training has been well st…

cs.CV2024

UniMed-CLIP: Towards a Unified Image-Text Pretraining Paradigm for Diverse Medical Imaging Modalities

Muhammad Uzair Khattak, Shahina Kunhimon, Muzammal Naseer +2

Vision-Language Models (VLMs) trained via contrastive learning have achieved notable success in natural image tasks. However, their application in the medical domain remains limite…

cs.CV2024

Language Guided Domain Generalized Medical Image Segmentation

Shahina Kunhimon, Muzammal Naseer, Salman Khan +1

Single source domain generalization (SDG) holds promise for more reliable and consistent image segmentation across real-world clinical settings particularly in the medical domain,…

eess.IV2023

Learnable Weight Initialization for Volumetric Medical Image Segmentation

Shahina Kunhimon, Abdelrahman Shaker, Muzammal Naseer +2

Hybrid volumetric medical image segmentation models, combining the advantages of local convolution and global attention, have recently received considerable attention. While mainly…

cs.CV2022★ 2 cited

Adversarial Pixel Restoration as a Pretext Task for Transferable Perturbations

Hashmat Shadab Malik, Shahina K Kunhimon, Muzammal Naseer +2

Transferable adversarial attacks optimize adversaries from a pretrained surrogate model and known label space to fool the unknown black-box models. Therefore, these attacks are res…