All Publications

(* indicates first author/equal contribution. Author name ordered alphabetically by last name.)

The following list maybe incomplete. Please visit my Google Scholar profile for the most up-to-date information.

Model Merging Teaser

Merge Now, Regret Later: The Hidden Cost of Model Merging Is Adversarial Transferability

Ankit Gangwal and Aaryan Ajay Sharma*
Under Review at AsiaCCS 2026

[arXiv]

GENIE Teaser

GENIE: Watermarking Graph Neural Networks for Link Prediction

VSP Bachina*, Ankit Gangwal, Aaryan Ajay Sharma*, and Charu Sharma
Transactions on Machine Learning Research (TMLR)

[arXiv]

Poster Teaser

Investigating Transferability of Adversarial Examples in Model Merging

Ankit Gangwal and Aaryan Ajay Sharma*
Proceedings of the 20th ACM Asia Conference on Computer and Communications Security (AsiaCCS 2025)

[DOI] [PDF]