PromptLocate: Localizing Prompt Injection Attacks
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908598446063616 |
|---|---|
| author | Jia, Yuqi Liu, Yupei Shao, Zedian Jia, Jinyuan Gong, Neil |
| author_facet | Jia, Yuqi Liu, Yupei Shao, Zedian Jia, Jinyuan Gong, Neil |
| contents | Prompt injection attacks deceive a large language model into completing an attacker-specified task instead of its intended task by contaminating its input data with an injected prompt, which consists of injected instruction(s) and data. Localizing the injected prompt within contaminated data is crucial for post-attack forensic analysis and data recovery. Despite its growing importance, prompt injection localization remains largely unexplored. In this work, we bridge this gap by proposing PromptLocate, the first method for localizing injected prompts. PromptLocate comprises three steps: (1) splitting the contaminated data into semantically coherent segments, (2) identifying segments contaminated by injected instructions, and (3) pinpointing segments contaminated by injected data. We show PromptLocate accurately localizes injected prompts across eight existing and eight adaptive attacks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_12252 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | PromptLocate: Localizing Prompt Injection Attacks Jia, Yuqi Liu, Yupei Shao, Zedian Jia, Jinyuan Gong, Neil Cryptography and Security Artificial Intelligence Prompt injection attacks deceive a large language model into completing an attacker-specified task instead of its intended task by contaminating its input data with an injected prompt, which consists of injected instruction(s) and data. Localizing the injected prompt within contaminated data is crucial for post-attack forensic analysis and data recovery. Despite its growing importance, prompt injection localization remains largely unexplored. In this work, we bridge this gap by proposing PromptLocate, the first method for localizing injected prompts. PromptLocate comprises three steps: (1) splitting the contaminated data into semantically coherent segments, (2) identifying segments contaminated by injected instructions, and (3) pinpointing segments contaminated by injected data. We show PromptLocate accurately localizes injected prompts across eight existing and eight adaptive attacks. |
| title | PromptLocate: Localizing Prompt Injection Attacks |
| topic | Cryptography and Security Artificial Intelligence |
| url | https://arxiv.org/abs/2510.12252 |