Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Jin, Hyundong, Sung, Sicheol, Park, Shinwoo, Baik, SeungYeop, Han, Yo-Sub
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2506.00089
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866908562513461248
author Jin, Hyundong
Sung, Sicheol
Park, Shinwoo
Baik, SeungYeop
Han, Yo-Sub
author_facet Jin, Hyundong
Sung, Sicheol
Park, Shinwoo
Baik, SeungYeop
Han, Yo-Sub
contents The reasoning, writing, text-editing, and retrieval capabilities of proprietary large language models (LLMs) have advanced rapidly, providing users with an ever-expanding set of functionalities. However, this growing utility has also led to a serious societal concern: the over-reliance on LLMs. In particular, users increasingly delegate tasks such as homework, assignments, or the processing of sensitive documents to LLMs without meaningful engagement. This form of over-reliance and misuse is emerging as a significant social issue. In order to mitigate these issues, we propose a method injecting imperceptible phantom tokens into documents, which causes LLMs to generate outputs that appear plausible to users but are in fact incorrect. Based on this technique, we introduce TRAPDOC, a framework designed to deceive over-reliant LLM users. Through empirical evaluation, we demonstrate the effectiveness of our framework on proprietary LLMs, comparing its impact against several baselines. TRAPDOC serves as a strong foundation for promoting more responsible and thoughtful engagement with language models. Our code is available at https://github.com/jindong22/TrapDoc.
format Preprint
id arxiv_https___arxiv_org_abs_2506_00089
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle TRAPDOC: Deceiving LLM Users by Injecting Imperceptible Phantom Tokens into Documents
Jin, Hyundong
Sung, Sicheol
Park, Shinwoo
Baik, SeungYeop
Han, Yo-Sub
Computers and Society
Artificial Intelligence
The reasoning, writing, text-editing, and retrieval capabilities of proprietary large language models (LLMs) have advanced rapidly, providing users with an ever-expanding set of functionalities. However, this growing utility has also led to a serious societal concern: the over-reliance on LLMs. In particular, users increasingly delegate tasks such as homework, assignments, or the processing of sensitive documents to LLMs without meaningful engagement. This form of over-reliance and misuse is emerging as a significant social issue. In order to mitigate these issues, we propose a method injecting imperceptible phantom tokens into documents, which causes LLMs to generate outputs that appear plausible to users but are in fact incorrect. Based on this technique, we introduce TRAPDOC, a framework designed to deceive over-reliant LLM users. Through empirical evaluation, we demonstrate the effectiveness of our framework on proprietary LLMs, comparing its impact against several baselines. TRAPDOC serves as a strong foundation for promoting more responsible and thoughtful engagement with language models. Our code is available at https://github.com/jindong22/TrapDoc.
title TRAPDOC: Deceiving LLM Users by Injecting Imperceptible Phantom Tokens into Documents
topic Computers and Society
Artificial Intelligence
url https://arxiv.org/abs/2506.00089