Invisible Text Injection and Peer Review by AI Models

Byungjin Choi; Tae Joon Jun; Joung Won Sung; Il Woo Park; Jeong-Moo Lee; Soo Ick Cho; Hyung Jun Park; Ro Woon Lee; Jungyo Suh

doi:10.1001/jamanetworkopen.2025.52099

January 16, 2026JAMA Network OpenOpen Access

Invisible Text Injection and Peer Review by AI Models

View Full Paper

Ask AI

Bookmark

Share

Key Points

The study aims to evaluate how susceptible leading large language models are to invisible text injection in the context of peer review.
Assessed commercial large language models for their vulnerability to text manipulation.
Conducted simulations of the peer review process to test models.
Evaluated the impacts of invisible text on model outputs.
Identified significant vulnerabilities in AI models to invisible text manipulation.
Found that such manipulations can affect the quality of peer review.
Demonstrated that AI's reliance on textual input makes it susceptible to strategic bias.

Implication

Quality improvement study assesses AI vulnerability to text manipulation in simulated medical peer review, indicating potential risks in academic integrity.

Abstract

This quality improvement study assesses the vulnerability of leading commercial large language models to invisible text injection manipulation in simulated medical peer review.

Discussion

No takes yet. Share an insight, caveat, or question.

Cite This Study

Choi et al. (2026) studied this question.

synapsesocial.com/papers/696c772aeb60fb80d139561f https://doi.org/10.1001/jamanetworkopen.2025.52099

View Full Paper

Ask AI

Bookmark

Share

Invisible Text Injection and Peer Review by AI Models

Key Points

Implication

Abstract

Discussion

Cite This Study

Invisible Text Injection and Peer Review by AI Models

Key Points

Implication

Abstract

Discussion

Cite This Study

Keep reading

Keep reading