3 papers
cs.CV2025
TAIGen: Training-Free Adversarial Image Generation via Diffusion Models
Susim Roy, Anubhooti Jain, Mayank Vatsa +1
Adversarial attacks from generative models often produce low-quality images and require substantial computational resources. Diffusion models, though capable of high-quality genera…
cs.CV2024
Discerning the Chaos: Detecting Adversarial Perturbations while Disentangling Intentional from Unintentional Noises
Anubhooti Jain, Susim Roy, Kwanit Gupta +2
Deep learning models, such as those used for face recognition and attribute prediction, are susceptible to manipulations like adversarial noise and unintentional noise, including G…
cs.CV2023
Adventures of Trustworthy Vision-Language Models: A Survey
Mayank Vatsa, Anubhooti Jain, Richa Singh
Recently, transformers have become incredibly popular in computer vision and vision-language tasks. This notable rise in their usage can be primarily attributed to the capabilities…