Conference on Neural Information Processing Systems (NeurIPS), 2026
We propose a local geometric framework for identifying invariant semantic subspaces in transformer-based language models, with applications to zero-shot model attribution across diverse LLM architectures.
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026
TIACam is a text-anchored invariant feature learning framework for camera-robust zero-watermarking that embeds messages in a distortion-invariant feature space.
IEEE Transactions on Artificial Intelligence 2025
Prompt-based LLM watermarking framework that embeds detectable signals in model responses without modifying weights or data.
International Conf. on Computational Science & Computational Intelligence 2023
Watermark embedding and extraction method resilient to geometric and photometric attacks using ViT-based cross-attention and invariant domain learning.
International Conf. on Computational Science & Computational Intelligence 2022
A lightweight differentiable layer that learns perspective transformations within the network forward pass, improving robustness to viewpoint changes.