4 papers
Invariant Features in Language Models: Geometric Characterization and Model Attribution
Agnibh Dasgupta, Abdullah Tanvir, Xin Zhong
Language models exhibit strong robustness to paraphrasing, suggesting that semantic information may be encoded through stable internal representations, yet the structure and origin…
TIACam: Text-Anchored Invariant Feature Learning with Auto-Augmentation for Camera-Robust Zero-Watermarking
Abdullah All Tanvir, Agnibh Dasgupta, Xin Zhong
Camera recapture introduces complex optical degradations, such as perspective warping, illumination shifts, and Moiré interference, that remain challenging for deep watermarking sy…
Watermarking Language Models through Language Models
Agnibh Dasgupta, Abdullah Tanvir, Xin Zhong
Watermarking the outputs of large language models (LLMs) is critical for provenance tracing, content regulation, and model accountability. Existing approaches often rely on access…
Robust Image Watermarking based on Cross-Attention and Invariant Domain Learning
Agnibh Dasgupta, Xin Zhong
Image watermarking involves embedding and extracting watermarks within a cover image, with deep learning approaches emerging to bolster generalization and robustness. Predominantly…