ChatGPT: Excellent Paper! Accept It. Editor: Imposter Found! Review Rejected

TL;DR

This paper investigates the vulnerabilities and defenses related to the use of Large Language Models like ChatGPT in scientific peer review, highlighting risks of bias and proposing detection strategies.

Contribution

It introduces an 'inject-and-detect' method to identify LLM-generated reviews, enhancing the integrity of the peer-review process against prompt injection attacks.

Findings

Demonstrated how hidden prompts can bias LLM reviews.

Proposed a detection strategy using invisible trigger prompts.

Outlined ethical safeguards for deploying the detection method.

Abstract

Large Language Models (LLMs) like ChatGPT are now widely used in writing and reviewing scientific papers. While this trend accelerates publication growth and reduces human workload, it also introduces serious risks. Papers written or reviewed by LLMs may lack real novelty, contain fabricated or biased results, or mislead downstream research that others depend on. Such issues can damage reputations, waste resources, and even endanger lives when flawed studies influence medical or safety-critical systems. This research explores both the offensive and defensive sides of this growing threat. On the attack side, we demonstrate how an author can inject hidden prompts inside a PDF that secretly guide or "jailbreak" LLM reviewers into giving overly positive feedback and biased acceptance. On the defense side, we propose an "inject-and-detect" strategy for editors, where invisible trigger prompts are embedded into papers; if a review repeats or reacts to these triggers, it reveals that the review was generated by an LLM, not a human. This method turns prompt injections from vulnerability into a verification tool. We outline our design, expected model behaviors, and ethical safeguards for deployment. The goal is to expose how fragile today's peer-review process becomes under LLM influence and how editorial awareness can help restore trust in scientific evaluation.