Year: 2025
Type: preprint
Abstract: Large Language Models (LLMs) are widely deployed in applications that accept user-submitted content, such as uploaded documents or pasted text, for tasks like summarization and question answering. In this paper, we identify a new class of attacks, prompt in content injection, where adversarial instructions are embedded in seemingly benign inputs. When processed by the LLM, these hidden prompts can manipulate outputs without user awareness or system compromise, leading to biased summaries, fabricated claims, or misleading suggestions. We demonstrate the feasibility of such attacks across popular platforms, analyze their root causes including prompt concatenation and insufficient input isolation, and discuss mitigation strategies. Our findings reveal a subtle yet practical threat in real-world LLM workflows.
Source: arXiv (Cornell University)
Authors: Lian, Zhuotao, Wang, Weiyu, Zeng, Qingkui, Nakanishi, Toru, Kitasuka, Teruaki, Su, Chunhua
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W7078600346
Cites:
Cited by:
Related to: