4 papers
Identity-Focused Inference and Extraction Attacks on Diffusion Models
Jayneel Vora, Aditya Krishnan, Nader Bouacida +2
The increasing reliance on diffusion models for generating synthetic images has amplified concerns about the unauthorized use of personal data, particularly facial images, in model…
PTQ4ADM: Post-Training Quantization for Efficient Text Conditional Audio Diffusion Models
Jayneel Vora, Aditya Krishnan, Nader Bouacida +2
Denoising diffusion models have emerged as state-of-the-art in generative tasks across image, audio, and video domains, producing high-quality, diverse, and contextually relevant d…
Augmented Efficiency: Reducing Memory Footprint and Accelerating Inference for 3D Semantic Segmentation through Hybrid Vision
Aditya Krishnan, Jayneel Vora, Prasant Mohapatra
Semantic segmentation has emerged as a pivotal area of study in computer vision, offering profound implications for scene understanding and elevating human-machine interactions acr…
FedDM: Enhancing Communication Efficiency and Handling Data Heterogeneity in Federated Diffusion Models
Jayneel Vora, Nader Bouacida, Aditya Krishnan +1
We introduce FedDM, a novel training framework designed for the federated training of diffusion models. Our theoretical analysis establishes the convergence of diffusion models whe…