2 citations · 4 across the 33 of their papers we have counts for
Showing 2025 · cs.CRShow all
2 papers · 2 filters
cs.CR2025
DITTO: A Spoofing Attack Framework on Watermarked LLMs via Knowledge Distillation
Hyeseon An, Shinwoo Park, Suyeon Woo +1
The promise of LLM watermarking rests on a core assumption that a specific watermark proves authorship by a specific model. We demonstrate that this assumption is dangerously flawe…
cs.CR2025★ 1 cited
Marking Code Without Breaking It: Code Watermarking for Detecting LLM-Generated Code
Jungin Kim, Shinwoo Park, Yo-Sub Han
Identifying LLM-generated code through watermarking poses a challenge in preserving functional correctness. Previous methods rely on the assumption that watermarking high-entropy t…