activity
20242026
most citedGenerating Universal Adversarial Perturbations for Quantum Classifiers

7 citations · 8 across the 3 of their papers we have counts for

collaborators
Showing cs.CVShow all

2 papers · 1 filter

cs.CV2026

It Takes Little to Rewrite Perception: Targeted Semantic Substitution in Vision-Language Models at

Binchi Zhang, Atrisha Sarkar, Apurva Narayan

Vision Language Models (VLMs) are widely deployed in safety-critical scenarios, and understanding to which extent they can be controlled by adversarial perturbation is a prerequisi…

cs.CV2025

Filtered-ViT: A Robust Defense Against Multiple Adversarial Patch Attacks

Aja Khanal, Ahmed Faid, Apurva Narayan

Deep learning vision systems are increasingly deployed in safety-critical domains such as healthcare, yet they remain vulnerable to small adversarial patches that can trigger miscl…