Cover Image

When Your Reviewer is an LLM: Biases, Divergence, and Prompt Injection Risks in Peer Review

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhu, Changjia, Xiong, Junjie, Ma, Renkai, Lu, Zhicong, Liu, Yao, Li, Lingyao
Format:	Preprint
Published:	2025
Subjects:	Computers and Society Cryptography and Security
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

LLM-as-a-Reviewer: Benchmarking Their Ability, Divergence, and Prompt Injection Resistance as Paper Reviewers
by: Li, Lingyao, et al.
Published: (2026)

Invisible Prompts, Visible Threats: Malicious Font Injection in External Resources for Large Language Models
by: Xiong, Junjie, et al.
Published: (2025)

COGNITION: From Evaluation to Defense against Multimodal LLM CAPTCHA Solvers
by: Wang, Junyu, et al.
Published: (2025)

Prompt Injection Vulnerability of Consensus Generating Applications in Digital Democracy
by: Gudiño-Rosero, Jairo, et al.
Published: (2025)

Misleading Large Language Models used (or misused) in Scientific Peer-Reviewing via Hidden Prompt-Injection Attacks
by: Collu, Matteo Gioele, et al.
Published: (2025)

From Prompt Injections to SQL Injection Attacks: How Protected is Your LLM-Integrated Web Application?
by: Pedro, Rodrigo, et al.
Published: (2023)

AI Agents May Always Fall for Prompt Injections
by: Abdelnabi, Sahar, et al.
Published: (2026)

Fingerprinting LLMs via Prompt Injection
by: Hu, Yuepeng, et al.
Published: (2025)

AttriGuard: Defeating Indirect Prompt Injection in LLM Agents via Causal Attribution of Tool Invocations
by: He, Yu, et al.
Published: (2026)

Democratizing Federated Learning with Blockchain and Multi-Task Peer Prediction
by: Witt, Leon, et al.
Published: (2026)

When Reject Turns into Accept: Quantifying the Vulnerability of LLM-Based Scientific Reviewers to Indirect Prompt Injection
by: Sahoo, Devanshu, et al.
Published: (2025)

When Skills Lie: Hidden-Comment Injection in LLM Agents
by: Wang, Qianli, et al.
Published: (2026)

What's on Your Mind? Exploring Privacy of Mental Health Apps
by: Georgiou, Chloe, et al.
Published: (2026)

Cybersecurity Career Requirements: A Literature Review
by: Nkongolo, Mike, et al.
Published: (2023)

The Vulnerability of LLM Rankers to Prompt Injection Attacks
by: Yin, Yu, et al.
Published: (2026)

Toward Integrated Solutions: A Systematic Interdisciplinary Review of Cybergrooming Research
by: An, Heajun, et al.
Published: (2025)

A Comprehensive Analytical Review on Cybercrime in West Africa
by: Adewopo, Victor, et al.
Published: (2024)

A Systematic Literature Review on the NIS2 Directive
by: Ruohonen, Jukka
Published: (2024)

Global Web, Local Privacy? An International Review of Web Tracking
by: Yu, Harry, et al.
Published: (2026)

BadScientist: Can a Research Agent Write Convincing but Unsound Papers that Fool LLM Reviewers?
by: Jiang, Fengqing, et al.
Published: (2025)

Prompt Injection Attack to Tool Selection in LLM Agents
by: Shi, Jiawen, et al.
Published: (2025)

Cybersecurity Guidance for Smart Homes: A Cross-National Review of Government Sources
by: Jüttner, Victor, et al.
Published: (2026)

"Give a Positive Review Only": An Early Investigation Into In-Paper Prompt Injection Attacks and Defenses for AI Reviewers
by: Zhou, Qin, et al.
Published: (2025)

Detecting LLM-Generated Peer Reviews
by: Rao, Vishisht, et al.
Published: (2025)

When AI Meets the Web: Prompt Injection Risks in Third-Party AI Chatbot Plugins
by: Kaya, Yigitcan, et al.
Published: (2025)

ObliInjection: Order-Oblivious Prompt Injection Attack to LLM Agents with Multi-source Data
by: Wang, Reachal, et al.
Published: (2025)

AgentVisor: Defending LLM Agents Against Prompt Injection via Semantic Virtualization
by: Ying, Zonghao, et al.
Published: (2026)

SecureForge: Finding and Preventing Vulnerabilities in LLM-Generated Code via Prompt Optimization
by: Liu, Houjun, et al.
Published: (2026)

Towards Trustworthy AI: Characterizing User-Reported Risks across LLMs "In the Wild"
by: Li, Lingyao, et al.
Published: (2025)

Is Your Prompt Safe? Investigating Prompt Injection Attacks Against Open-Source LLMs
by: Wang, Jiawen, et al.
Published: (2025)

What to Consider When Considering Differential Privacy for Policy
by: Nanayakkara, Priyanka, et al.
Published: (2024)

Review-Incorporated Model-Agnostic Profile Injection Attacks on Recommender Systems
by: Yang, Shiyi, et al.
Published: (2024)

To Protect the LLM Agent Against the Prompt Injection Attack with Polymorphic Prompt
by: Wang, Zhilong, et al.
Published: (2025)

SoK: Reviewing Two Decades of Security, Privacy, Accessibility, and Usability Studies on Internet of Things for Older Adults
by: Saka, Suleiman, et al.
Published: (2025)

SafeReview: Defending LLM-based Review Systems Against Adversarial Hidden Prompts
by: Xin, Yuan, et al.
Published: (2026)

How Safe Is Your Data in Connected and Autonomous Cars: A Consumer Advantage or a Privacy Nightmare ?
by: Chougule, Amit, et al.
Published: (2026)

Silent Egress: When Implicit Prompt Injection Makes LLM Agents Leak Without a Trace
by: Lan, Qianlong, et al.
Published: (2026)

SemFuzz: A Semantics-Aware Fuzzing Framework for Network Protocol Implementations
by: Sun, Yanbang, et al.
Published: (2026)

Is Your AI Truly Yours? Leveraging Blockchain for Copyrights, Provenance, and Lineage
by: Wang, Qin, et al.
Published: (2024)

Prompt injections as a tool for preserving identity in GAI image descriptions
by: Glazko, Kate, et al.
Published: (2025)