3 papers
cs.CL2026
Distribution Corrected Offline Data Distillation for Large Language Models
Yumeng Zhang, Zhengbang Yang, Yevin Nikhel Goonatilake +1
Distilling reasoning traces from strong large language models into smaller ones is a promising route to improve intelligence in resource-constrained settings. Existing approaches f…
cs.CR2026
Removing the Watermark Is Not Enough: Forensic Stealth in Generative-AI Watermark Removal
Yevin Nikhel Goonatilake, Giuseppe Ateniese
The literature on watermark removal has largely asked whether an attacker can make the watermark verifier fail while preserving the appearance of the image. This is a useful test,…
cs.CR2025
The Coding Limits of Robust Watermarking for Generative Models
Danilo Francati, Yevin Nikhel Goonatilake, Shubham Pawar +2
We study a basic question about cryptographic watermarking for generative models: how reliable can a watermark remain when an adversary is allowed to corrupt the encoded signal? To…