Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| 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 |