activity
20242026
collaborators

7 papers

cs.CV2026

Pulling The REINS: Training-Free Safety Alignment of Video Diffusion Models via Representation Steering

Rohit Kundu, Arindam Dutta, Sarosij Bose +2

Open-weight video diffusion models can generate photorealistic unsafe content, from violence to misinformation, yet existing defenses either require expensive safety fine-tuning th…

cs.CV2026

SAGA: Source Attribution of Generative AI Videos

Rohit Kundu, Vishal Mohanty, Hao Xiong +3

The proliferation of generative AI has led to hyper-realistic synthetic videos, escalating misuse risks and outstripping binary real/fake detectors. We introduce SAGA (Source Attri…

cs.CV2025

TruthLens: Visual Grounding for Universal DeepFake Reasoning

Rohit Kundu, Shan Jia, Vishal Mohanty +2

Detecting DeepFakes has become a crucial research area as the widespread use of AI image generators enables the effortless creation of face-manipulated and fully synthetic content,…

cs.CV2025

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

Rohit Kundu, Hao Xiong, Vishal Mohanty +2

Existing DeepFake detection techniques primarily focus on facial manipulations, such as face-swapping or lip-syncing. However, advancements in text-to-video (T2V) and image-to-vide…

cs.CV2025

Repurposing SAM for User-Defined Semantics Aware Segmentation

Rohit Kundu, Sudipta Paul, Arindam Dutta +1

The Segment Anything Model (SAM) excels at generating precise object masks from input prompts but lacks semantic awareness, failing to associate its generated masks with specific o…

cs.LG2025

Towards Source-Free Machine Unlearning

Sk Miraj Ahmed, Umit Yigit Basaran, Dripta S. Raychaudhuri +5

As machine learning becomes more pervasive and data privacy regulations evolve, the ability to remove private or copyrighted information from trained models is becoming an increasi…