2 citations · 4 across the 33 of their papers we have counts for
5 papers · 1 filter
Grammar-Guided Code Watermarking with Green Temperature
Hyundong Jin, Hyeseon An, Soohan Lim +1
Large language model watermarking embeds detectable statistical signals during decoding, but the resulting changes to token probabilities can degrade generation quality. This trade…
SEW: Style-Encoded Watermarking of LLM-Generated Code
Soohan Lim, Hyundong Jin, Yo-Sub Han
Code watermarking supports provenance tracking for code generated by LLMs. Modifying token selection to embed watermarks as an LLM generates code can create a trade-off between det…
Sequential Behavioral Watermarking for LLM Agents
Hyeseon An, Shinwoo Park, Dongsu Kim +1
LLM-based agents act through sequences of executable decisions, but their trajectories provide little evidence of which agent or policy produced them, making provenance, ownership,…
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…
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…