Amit K. Roy-Chowdhury

6

Papers

16

Total Citations

Papers (6)

Towards a Universal Synthetic Video Detector: From Face or Background Manipulations to Fully AI-Generated Content

Towards Source-Free Machine Unlearning

Layer-wise Alignment: Examining Safety Alignment Across Image Encoder Layers in Vision Language Models

Gradient Inversion Attacks on Parameter-Efficient Fine-Tuning

Conformal Prediction and MLLM aided Uncertainty Quantification in Scene Graph Generation

AdMiT: Adaptive Multi-Source Tuning in Dynamic Environments