TRAPDOC: Deceiving LLM Users by Injecting Imperceptible Phantom Tokens into Documents

Documenti analoghi

• A Framework for Quantum Finite-State Languages with Density Mapping
  di: Baik, SeungYeop, et al.
  Pubblicazione: (2024)
• Detection of LLM-Paraphrased Code and Identification of the Responsible LLM Using Coding Style Features
  di: Park, Shinwoo, et al.
  Pubblicazione: (2025)
• Steering Language Models Before They Speak: Logit-Level Interventions
  di: An, Hyeseon, et al.
  Pubblicazione: (2026)
• From Intuition to Calibrated Judgment: A Rubric-Based Expert-Panel Study of Human Detection of LLM-Generated Korean Text
  di: Park, Shinwoo, et al.
  Pubblicazione: (2026)
• WaterMod: Modular Token-Rank Partitioning for Probability-Balanced LLM Watermarking
  di: Park, Shinwoo, et al.
  Pubblicazione: (2025)