Prompt Injection Attacks on LLM Generated Reviews of Scientific Publications

Janis Keuper
9/12/2025
cs.LG

No confident code implementation found for this paper.

Abstract

The ongoing intense discussion on rising LLM usage in the scientific peer-review process has recently been mingled by reports of authors using hidden prompt injections to manipulate review scores. Since the existence of such "attacks" - although seen by some commentators as "self-defense" - would have a great impact on the further debate, this paper investigates the practicability and technical success of the described manipulations. Our systematic evaluation uses 1k reviews of 2024 ICLR papers generated by a wide range of LLMs shows two distinct results: I) very simple prompt injections are indeed highly effective, reaching up to 100% acceptance scores. II) LLM reviews are generally biased toward acceptance (>95% in many models). Both results have great impact on the ongoing discussions on LLM usage in peer-review.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Multilingual Hidden Prompt Injection Attacks on LLM-Based Academic Reviewing

87% match2025

When Reject Turns into Accept: Quantifying the Vulnerability of LLM-Based Scientific Reviewers to Indirect Prompt Injection

85% match2025

"Give a Positive Review Only": An Early Investigation Into In-Paper Prompt Injection Attacks and Defenses for AI Reviewers

84% match2025

Paraphrasing Adversarial Attack on LLM-as-a-Reviewer

84% match2026

Hidden Prompts in Manuscripts Exploit AI-Assisted Peer Review

84% match2025

Breaking the Reviewer: Assessing the Vulnerability of Large Language Models in Automated Peer Review Under Textual Adversarial Attacks

83% match2025

Cite this paper

@article{keuper2025prompt,
  title  = {Prompt Injection Attacks on LLM Generated Reviews of Scientific Publications},
  author = {Janis Keuper},
  year   = {2025},
  eprint = {2509.10248},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2509.10248v3}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2509.10248.svg)](https://codeofpaper.com/paper/2509.10248)

Discussion