conftrace_

watermark radioactivity

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

knowledge distillation (2) paraphrasing training (1) text authorship (1) large language model (1) llm watermarking (1) unauthorized distillation (1) model protection (1) watermark removal (1) spoofing attack (1) model compression (1)

Papers

DITTO: A Spoofing Attack Framework on Watermarked LLMs via Knowledge Distillation EACL 2026 Can LLM Watermarks Robustly Prevent Unauthorized Knowledge Distillation? ACL 2025