Cover Image

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

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Sahoo, Devanshu, Prasad, Manish, Majhi, Vasudev, Singh, Jahnvi, Chamola, Vinay, Sinha, Yash, Mandal, Murari, Kumar, Dhruv
Format:	Preprint
Published:	2025
Subjects:	Artificial Intelligence Computation and Language Cryptography and Security
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

The Compliance Paradox: Semantic-Instruction Decoupling in Automated Academic Code Evaluation
by: Sahoo, Devanshu, et al.
Published: (2026)

How to Trick Your AI TA: A Systematic Study of Academic Jailbreaking in LLM Code Evaluation
by: Sahoo, Devanshu, et al.
Published: (2025)

Beyond Accuracy: Diagnosing Algebraic Reasoning Failures in LLMs Across Nine Complexity Dimensions
by: Patil, Parth, et al.
Published: (2026)

Measuring Representation Robustness in Large Language Models for Geometry
by: Jawandhia, Vedant, et al.
Published: (2026)

Distill to Delete: Unlearning in Graph Networks with Knowledge Distillation
by: Sinha, Yash, et al.
Published: (2023)

Multi-Modal Recommendation Unlearning for Legal, Licensing, and Modality Constraints
by: Sinha, Yash, et al.
Published: (2024)

UnStar: Unlearning with Self-Taught Anti-Sample Reasoning for LLMs
by: Sinha, Yash, et al.
Published: (2024)

Blockchain‐Based Cognitive Health Monitoring Using Incremental Learning
by: Shashank Srivastava, et al.
Published: (2026)

Split Learning-Enabled Framework for Secure and Light-weight Internet of Medical Things Systems
by: Sai, Siva, et al.
Published: (2025)

Accept-Reject Lasso
by: Liu, Yanxin, et al.
Published: (2025)

"I Strongly Suspect This Website Is a Scam": Benchmarking PII Leakage and Detection without Defense in Autonomous Web Agents
by: Roy, Soham, et al.
Published: (2026)

Relative Overfitting and Accept-Reject Framework
by: Liu, Yanxin, et al.
Published: (2025)

Step-by-Step Reasoning Attack: Revealing 'Erased' Knowledge in Large Language Models
by: Sinha, Yash, et al.
Published: (2025)

Online Conformal Selection with Accept-to-Reject Changes
by: Liu, Kangdao, et al.
Published: (2025)

CricBench: A Multilingual Benchmark for Evaluating LLMs in Cricket Analytics
by: Agarwal, Parth, et al.
Published: (2025)

Accepted with Minor Revisions: Value of AI-Assisted Scientific Writing
by: Hazra, Sanchaita, et al.
Published: (2025)

LLM-as-a-Judge for Time Series Explanations
by: Sivalingam, Preetham, et al.
Published: (2026)

Depth-Dependent Indirect Prompt Injection in Tool-Calling ReAct Agents: Injection Depth, Payload Framing, and Turn-Budget Sensitivity
by: Rashidi, Mohammadreza
Published: (2026)

BITS Pilani at SemEval-2026 Task 9: Structured Supervised Fine-Tuning with DPO Refinement for Polarization Detection
by: Gupta, Atharva, et al.
Published: (2026)

ReviewEval: An Evaluation Framework for AI-Generated Reviews
by: Garg, Madhav Krishan, et al.
Published: (2025)

How Vulnerable Are AI Agents to Indirect Prompt Injections? Insights from a Large-Scale Public Competition
by: Dziemian, Mateusz, et al.
Published: (2026)

Defending Against Indirect Prompt Injection Attacks With Spotlighting
by: Hines, Keegan, et al.
Published: (2024)

Defending against Indirect Prompt Injection by Instruction Detection
by: Wen, Tongyu, et al.
Published: (2025)

Can Indirect Prompt Injection Attacks Be Detected and Removed?
by: Chen, Yulin, et al.
Published: (2025)

The Readability of Published, Accepted, and Rejected Papers Appearing in "College & Research Libraries."
by: Metoyer-Duran, Cheryl
Published: (1993)

Accept or Reject: Factors Influencing Nonprofit Responses to Cannabis Industry Philanthropy
by: Jessica L. Berrett, et al.
Published: (2025)

OrgAccess: A Benchmark for Role Based Access Control in Organization Scale LLMs
by: Sanyal, Debdeep, et al.
Published: (2025)

Transient Turn Injection: Exposing Stateless Multi-Turn Vulnerabilities in Large Language Models
by: Rayhan, Naheed, et al.
Published: (2026)

Confidence is Not Competence
by: Sanyal, Debdeep, et al.
Published: (2025)

time2time: Causal Intervention in Hidden States to Simulate Rare Events in Time Series Foundation Models
by: Sanyal, Debdeep, et al.
Published: (2025)

Lessons from Defending Gemini Against Indirect Prompt Injections
by: Shi, Chongyang, et al.
Published: (2025)

A Novel Cloud-Based Diffusion-Guided Hybrid Model for High-Accuracy Accident Detection in Intelligent Transportation Systems
by: Sai, Siva, et al.
Published: (2025)

Generative Artificial Intelligence in STEM Education: A Review of Applications, Benefits and Challenges
by: Vinay Chamola, et al.
Published: (2026)

SkyCharge: Deploying Unmanned Aerial Vehicles for Dynamic Load Optimization in Solar Small Cell 5G Networks
by: Dave, Daksh, et al.
Published: (2023)

A novel generative adversarial network‐based super‐resolution approach for face recognition
by: Amit Chougule, et al.
Published: (2024)

Same Session Pre‐Emptive Endoscopic Ultrasound Guided Angioembolization of Perigastric Varices or Collaterals Facilitating Safe Vessel‐Free Endoscopic Ultrasound Guided Cystogastrostomy (With Video)
by: Jahnvi Dhar, et al.
Published: (2026)

Logic layer Prompt Control Injection (LPCI): A Novel Security Vulnerability Class in Agentic Systems
by: Atta, Hammad, et al.
Published: (2025)

ChatGPT: Excellent Paper! Accept It. Editor: Imposter Found! Review Rejected
by: Gharami, Kanchon, et al.
Published: (2025)

Agents Are All You Need for LLM Unlearning
by: Sanyal, Debdeep, et al.
Published: (2025)

Helpful to a Fault: Measuring Illicit Assistance in Multi-Turn, Multilingual LLM Agents
by: Talokar, Nivya, et al.
Published: (2026)