Cover Image

Systematically Analyzing Prompt Injection Vulnerabilities in Diverse LLM Architectures

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Benjamin, Victoria, Braca, Emily, Carter, Israel, Kanchwala, Hafsa, Khojasteh, Nava, Landow, Charly, Luo, Yi, Ma, Caroline, Magarelli, Anna, Mirin, Rachel, Moyer, Avery, Simpson, Kayla, Skawinski, Amelia, Heverin, Thomas
Format:	Preprint
Published:	2024
Subjects:	Cryptography and Security Artificial Intelligence Computation and Language Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Prompt Injection Evaluations: Refusal Boundary Instability and Artifact-Dependent Compliance in GPT-4-Series Models
by: Heverin, Thomas
Published: (2026)

Hipertexto: La convergencia de la teoria critica contemporanea y la tecnologia / George P. Landow ; traducción de Patrick Ducher
by: Landow, George P

Purification, characterization and analysis of sepia melanin from commercial sepia ink (Sepia Officinalis)
by: Mario Magarelli
Published: (2010)

Obtención de fertilizantes edáficos a partir del licor urea fosfato generado como subproducto en una planta de producción de urea fosfato cristal
by: Donato Magarelli
Published: (2011)

Model Context Protocol Threat Modeling and Analyzing Vulnerabilities to Prompt Injection with Tool Poisoning
by: Huang, Charoes, et al.
Published: (2026)

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

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

Investigating the Vulnerability of LLM-as-a-Judge Architectures to Prompt-Injection Attacks
by: Maloyan, Narek, et al.
Published: (2025)

ASPI: Seeking Ambiguity Clarification Amplifies Prompt Injection Vulnerability in LLM Agents
by: Sehwag, Udari Madhushani, et al.
Published: (2026)

A parameterized block-splitting preconditioner for indefinite least squares problem
by: Salkuyeh, Davod Khojasteh
Published: (2025)

Red Teaming the Mind of the Machine: A Systematic Evaluation of Prompt Injection and Jailbreak Vulnerabilities in LLMs
by: Pathade, Chetan
Published: (2025)

Nivel de conocimiento de la gestión de riesgos y el grado de madurez del SGC de los requisitos asociados a riesgos - Estudio de caso en una empresa petrolera mexicana
by: Ana Amelia Ordóñez Nava
Published: (2018)

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

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

VideoScoop: A Non-Traditional Domain-Independent Framework For Video Analysis
by: Billah, Hafsa
Published: (2025)

Exploring Salicornia species as potential health‐promoting food: chemical fingerprinting and assessment of their bioactivities
by: Emily Cioni, et al.
Published: (2026)

Queere Anti-Gewalt-Arbeit in Deutschland
by: Krenn, Charly
Published: (2025)

Combining Normalizing Flows and Quasi-Monte Carlo
by: Andral, Charly
Published: (2024)

Geochemistry of Tasiusaq peat core from Greenland
by: Massa, Charly
Published: (2021)

Calibrated ages of Tasiusaq peat core from Greenland
by: Massa, Charly
Published: (2021)

Age determination of Tasiusaq peat core from Greenland
by: Massa, Charly
Published: (2022)

Prompt Injection Attacks on Agentic Coding Assistants: A Systematic Analysis of Vulnerabilities in Skills, Tools, and Protocol Ecosystems
by: Maloyan, Narek, et al.
Published: (2026)

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

The Logic of the Laws
by: Moyer, D.S.
Published: (2016)

Birding in Ghana, West Africa
by: Moyer, David
Published: (1996)

Enumerative Discovery of Noncanonical Polypeptide Secondary Structures
by: Moyer, Adam
Published: (2024)

The Filth and the Fury 101
by: Moyer, Matthew
Published: (2007)

The Regional Library: Enhancing Services to Branch Users.
by: Moyer, Michael
Published: (1990)

Books Alive: Reading Incentive Programs for High School Students
by: Moyer, Mary
Published: (2007)

Bypassing Prompt Injection Detectors through Evasive Injections
by: Rahman, Md Jahedur, et al.
Published: (2026)

PromptLocate: Localizing Prompt Injection Attacks
by: Jia, Yuqi, et al.
Published: (2025)

Did You Forkget It? Detecting One-Day Vulnerabilities in Open-source ForksWith Global History Analysis
by: Lefeuvre, Romain, et al.
Published: (2025)

Selection of pushed pattern-forming fronts in the FitzHugh-Nagumo system
by: Avery, Montie, et al.
Published: (2026)

Defeating Prompt Injections by Design
by: Debenedetti, Edoardo, et al.
Published: (2025)

Prompt Injection as Role Confusion
by: Ye, Charles, et al.
Published: (2026)

Physics-informed coherent motions to predict Lagrangian trajectories
by: Khojasteh, Ali R, et al.
Published: (2025)

Positive semidefinite/positive semidefinite splitting iteration methods for solving nonsingular non-Hermitian positive semidefinite systems
by: Salkuyeh, Davod Khojasteh, et al.
Published: (2025)

A modified version of the PRESB preconditioner for a class of non-Hermitian complex systems of linear equations
by: Axelsson, Owe, et al.
Published: (2024)

Breaking the Protocol: Security Analysis of the Model Context Protocol Specification and Prompt Injection Vulnerabilities in Tool-Integrated LLM Agents
by: Maloyan, Narek, et al.
Published: (2026)

Fun-tuning: Characterizing the Vulnerability of Proprietary LLMs to Optimization-based Prompt Injection Attacks via the Fine-Tuning Interface
by: Labunets, Andrey, et al.
Published: (2025)