Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2508.19288 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914008476418048 |
|---|---|
| author | Shiomi, Kyohei Lian, Zhuotao Nakanishi, Toru Kitasuka, Teruaki |
| author_facet | Shiomi, Kyohei Lian, Zhuotao Nakanishi, Toru Kitasuka, Teruaki |
| contents | Large Language Models (LLMs) are increasingly used to generate dynamic dialogue for game NPCs. However, their integration raises new security concerns. In this study, we examine whether adversarial prompt injection can cause LLM-based NPCs to reveal hidden background secrets that are meant to remain undisclosed. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_19288 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Tricking LLM-Based NPCs into Spilling Secrets Shiomi, Kyohei Lian, Zhuotao Nakanishi, Toru Kitasuka, Teruaki Cryptography and Security Artificial Intelligence Large Language Models (LLMs) are increasingly used to generate dynamic dialogue for game NPCs. However, their integration raises new security concerns. In this study, we examine whether adversarial prompt injection can cause LLM-based NPCs to reveal hidden background secrets that are meant to remain undisclosed. |
| title | Tricking LLM-Based NPCs into Spilling Secrets |
| topic | Cryptography and Security Artificial Intelligence |
| url | https://arxiv.org/abs/2508.19288 |