Imagen de Portada

Exploring Potential Prompt Injection Attacks in Federated Military LLMs and Their Mitigation

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Lee, Youngjoon, Park, Taehyun, Lee, Yunho, Gong, Jinu, Kang, Joonhyuk
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Embedding Byzantine Fault Tolerance into Federated Learning via Consistency Scoring
por: Lee, Youngjoon, et al.
Publicado: (2024)

A Unified Benchmark of Federated Learning with Kolmogorov-Arnold Networks for Medical Imaging
por: Lee, Youngjoon, et al.
Publicado: (2025)

Generative AI-Powered Plugin for Robust Federated Learning in Heterogeneous IoT Networks
por: Lee, Youngjoon, et al.
Publicado: (2024)

Revisit the Stability of Vanilla Federated Learning Under Diverse Conditions
por: Lee, Youngjoon, et al.
Publicado: (2025)

CG-FKAN: Compressed-Grid Federated Kolmogorov-Arnold Networks for Communication Constrained Environment
por: Yu, Seunghun, et al.
Publicado: (2025)

Improving Generalizability of Kolmogorov-Arnold Networks via Error-Correcting Output Codes
por: Lee, Youngjoon, et al.
Publicado: (2025)

When to Stop Federated Learning: Zero-Shot Generation of Synthetic Validation Data with Generative AI for Early Stopping
por: Lee, Youngjoon, et al.
Publicado: (2025)

Debunking Optimization Myths in Federated Learning for Medical Image Classification
por: Lee, Youngjoon, et al.
Publicado: (2025)

Beyond Fixed Rounds: Data-Free Early Stopping for Practical Federated Learning
por: Lee, Youngjoon, et al.
Publicado: (2026)

ROK Defense M&S in the Age of Hyperscale AI: Concepts, Challenges, and Future Directions
por: Lee, Youngjoon, et al.
Publicado: (2024)

Forecasting-based Biomedical Time-series Data Synthesis for Open Data and Robust AI
por: Lee, Youngjoon, et al.
Publicado: (2025)

Resource-Aware Aggregation and Sparsification in Heterogeneous Ensemble Federated Learning
por: Ryum, Keumseo, et al.
Publicado: (2025)

MPIB: A Benchmark for Medical Prompt Injection Attacks and Clinical Safety in LLMs
por: Lee, Junhyeok, et al.
Publicado: (2026)

NeFL: Nested Model Scaling for Federated Learning with System Heterogeneous Clients
por: Kang, Honggu, et al.
Publicado: (2023)

Enhancing Prompt Injection Attacks to LLMs via Poisoning Alignment
por: Shao, Zedian, et al.
Publicado: (2024)

Mitigating Data Injection Attacks on Federated Learning
por: Shalom, Or, et al.
Publicado: (2023)

GeFL: Model-Agnostic Federated Learning with Generative Models
por: Kang, Honggu, et al.
Publicado: (2024)

TQ-DiT: Efficient Time-Aware Quantization for Diffusion Transformers
por: Hwang, Younghye, et al.
Publicado: (2025)

Decision-Path Patterns as Tree Reliability Signals: Path-based Adaptive Weighting for Random Forest Classification
por: Park, Youngjoon
Publicado: (2026)

Attention Tracker: Detecting Prompt Injection Attacks in LLMs
por: Hung, Kuo-Han, et al.
Publicado: (2024)

Adaptive Attacks Break Defenses Against Indirect Prompt Injection Attacks on LLM Agents
por: Zhan, Qiusi, et al.
Publicado: (2025)

Formalizing and Benchmarking Prompt Injection Attacks and Defenses
por: Liu, Yupei, et al.
Publicado: (2023)

FedEFC: Federated Learning Using Enhanced Forward Correction Against Noisy Labels
por: Yu, Seunghun, et al.
Publicado: (2025)

PIShield: Detecting Prompt Injection Attacks via Intrinsic LLM Features
por: Zou, Wei, et al.
Publicado: (2025)

Securing Large Language Models (LLMs) from Prompt Injection Attacks
por: Suri, Omar Farooq Khan, et al.
Publicado: (2025)

Mitigating Indirect Prompt Injection via Instruction-Following Intent Analysis
por: Kang, Mintong, et al.
Publicado: (2025)

Energy-Efficient Secure Communications via Joint Optimization of UAV Trajectory and Movable-Antenna Array Beamforming
por: Kim, Sanghyeok, et al.
Publicado: (2025)

MIMO Channel Prediction via Deep Learning-based Conformal Bayes Filter
por: Kim, Dongwon, et al.
Publicado: (2026)

Forward and Inverse Simulation of Pseudo-Two-Dimensional Model of Lithium-Ion Batteries Using Neural Networks
por: Lee, Myeong-Su, et al.
Publicado: (2024)

Prompt Injection Attacks on LLM Generated Reviews of Scientific Publications
por: Keuper, Janis
Publicado: (2025)

MaD-Scientist: AI-based Scientist solving Convection-Diffusion-Reaction Equations Using Massive PINN-Based Prior Data
por: Kang, Mingu, et al.
Publicado: (2024)

WebInject: Prompt Injection Attack to Web Agents
por: Wang, Xilong, et al.
Publicado: (2025)

LeakSealer: A Semisupervised Defense for LLMs Against Prompt Injection and Leakage Attacks
por: Panebianco, Francesco, et al.
Publicado: (2025)

SignSGD with Federated Defense: Harnessing Adversarial Attacks through Gradient Sign Decoding
por: Park, Chanho, et al.
Publicado: (2024)

PIG: Physics-Informed Gaussians as Adaptive Parametric Mesh Representations
por: Kang, Namgyu, et al.
Publicado: (2024)

Rate-Adaptive Quantization: A Multi-Rate Codebook Adaptation for Vector Quantization-based Generative Models
por: Seo, Jiwan, et al.
Publicado: (2024)

Machine Learning-Based Nonlinear Nudging for Chaotic Dynamical Systems
por: Oh, Jaemin, et al.
Publicado: (2025)

Error analysis for finite element operator learning methods for solving parametric second-order elliptic PDEs
por: Hong, Youngjoon, et al.
Publicado: (2024)

Prompt Injection Attacks on Large Language Models in Oncology
por: Clusmann, Jan, et al.
Publicado: (2024)

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