Cover Image

A Survey of LLM-Driven AI Agent Communication: Protocols, Security Risks, and Defense Countermeasures

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Kong, Dezhang, Lin, Shi, Xu, Zhenhua, Wang, Zhebo, Li, Minghao, Li, Yufeng, Zhang, Yilun, Peng, Hujin, Chen, Xiang, Sha, Zeyang, Li, Yuyuan, Lin, Changting, Wang, Xun, Liu, Xuan, Zhang, Ningyu, Chen, Chaochao, Wu, Chunming, Khan, Muhammad Khurram, Han, Meng
Format:	Preprint
Published:	2025
Subjects:	Cryptography and Security
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Web Fraud Attacks Against LLM-Driven Multi-Agent Systems
by: Kong, Dezhang, et al.
Published: (2025)

Fingerprint Vector: Enabling Scalable and Efficient Model Fingerprint Transfer via Vector Addition
by: Xu, Zhenhua, et al.
Published: (2024)

Copyright Protection for Large Language Models: A Survey of Methods, Challenges, and Trends
by: Xu, Zhenhua, et al.
Published: (2025)

NeuRel-Attack: Neuron Relearning for Safety Disalignment in Large Language Models
by: Zhou, Yi, et al.
Published: (2025)

DNF: Dual-Layer Nested Fingerprinting for Large Language Model Intellectual Property Protection
by: Xu, Zhenhua, et al.
Published: (2026)

ICPO: Illocution-Calibrated Policy Optimization for Multi-Turn Conversation
by: Wang, Zhebo, et al.
Published: (2026)

Class-wise Federated Unlearning: Harnessing Active Forgetting with Teacher-Student Memory Generation
by: Li, Yuyuan, et al.
Published: (2023)

RAID: An In-Training Defense against Attribute Inference Attacks in Recommender Systems
by: Feng, Xiaohua, et al.
Published: (2025)

Policy of Thoughts: Scaling LLM Reasoning via Test-time Policy Evolution
by: Jiao, Zhengbo, et al.
Published: (2026)

A Neuro-inspired Interpretation of Unlearning in Large Language Models through Sample-level Unlearning Difficulty
by: Feng, Xiaohua, et al.
Published: (2025)

UW-3DGS: Underwater 3D Reconstruction with Physics-Aware Gaussian Splatting
by: Xing, Wenpeng, et al.
Published: (2025)

HGMF: A Hierarchical Gaussian Mixture Framework for Scalable Tool Invocation within the Model Context Protocol
by: Xing, Wenpeng, et al.
Published: (2025)

A Survey on Recommendation Unlearning: Fundamentals, Taxonomy, Evaluation, and Open Questions
by: Li, Yuyuan, et al.
Published: (2024)

The Application of TF‐IDF in the Research of Flood and Drought Disaster Defense System
by: Qian Li, et al.
Published: (2025)

FedFACT: A Provable Framework for Controllable Group-Fairness Calibration in Federated Learning
by: Zhang, Li, et al.
Published: (2025)

UFO: Unfair-to-Fair Evolving Mitigates Unfairness in LLM-based Recommender Systems via Self-Play Fine-tuning
by: Zhang, Jiaming, et al.
Published: (2025)

AttnDiff: Attention-based Differential Fingerprinting for Large Language Models
by: Zhang, Haobo, et al.
Published: (2026)

Sharpness-Aware Minimization for Generalized Embedding Learning in Federated Recommendation
by: Yu, Fengyuan, et al.
Published: (2026)

MCP-Guard: A Multi-Stage Defense-in-Depth Framework for Securing Model Context Protocol in Agentic AI
by: Xing, Wenpeng, et al.
Published: (2025)

A Tampering Risk of Fiber-Based Frequency Synchronization Networks and Its Countermeasures
by: Dai, Hongfei, et al.
Published: (2024)

Demystifying the Optimal Fair Classifier in Multi-Class Classification
by: Zhang, Li, et al.
Published: (2026)

Taming the Long Tail: Efficient Item-wise Sharpness-Aware Minimization for LLM-based Recommender Systems
by: Zhang, Jiaming, et al.
Published: (2026)

TOFA: Training-Free One-Shot Federated Adaptation for Vision-Language Models
by: Zhang, Li, et al.
Published: (2025)

LLMs can be Dangerous Reasoners: Analyzing-based Jailbreak Attack on Large Language Models
by: Lin, Shi, et al.
Published: (2024)

Bridging the Gap Between Preference Alignment and Machine Unlearning
by: Feng, Xiaohua, et al.
Published: (2025)

BiFair: A Fairness-aware Training Framework for LLM-enhanced Recommender Systems via Bi-level Optimization
by: Zhang, Jiaming, et al.
Published: (2025)

Controllable Unlearning for Image-to-Image Generative Models via $\varepsilon$-Constrained Optimization
by: Feng, Xiaohua, et al.
Published: (2024)

Reproducibility Companion Paper: Making Users Indistinguishable: Attribute-wise Unlearning in Recommender Systems
by: Li, Yuyuan, et al.
Published: (2025)

LEGO: A Lightweight and Efficient Multiple-Attribute Unlearning Framework for Recommender Systems
by: Yu, Fengyuan, et al.
Published: (2025)

A Survey on Generative Model Unlearning: Fundamentals, Taxonomy, Evaluation, and Future Direction
by: Feng, Xiaohua, et al.
Published: (2025)

Dual Learning with Dynamic Knowledge Distillation and Soft Alignment for Partially Relevant Video Retrieval
by: Dong, Jianfeng, et al.
Published: (2025)

Prompt Stealing Attacks Against Large Language Models
by: Sha, Zeyang, et al.
Published: (2024)

WassFFed: Wasserstein Fair Federated Learning
by: Han, Zhongxuan, et al.
Published: (2024)

CURE4Rec: A Benchmark for Recommendation Unlearning with Deeper Influence
by: Chen, Chaochao, et al.
Published: (2024)

The Impact of Audio Watermarking on Audio Anti-Spoofing Countermeasures
by: Zhang, Zhenshan, et al.
Published: (2025)

UKnow: A Unified Knowledge Protocol with Multimodal Knowledge Graph Datasets for Reasoning and Vision-Language Pre-Training
by: Gong, Biao, et al.
Published: (2023)

LLM Security: Vulnerabilities, Attacks, Defenses, and Countermeasures
by: Aguilera-Martínez, Francisco, et al.
Published: (2025)

Post-Training Attribute Unlearning in Recommender Systems
by: Chen, Chaochao, et al.
Published: (2024)

Reproducibility Companion Paper:In-processing User Constrained Dominant Sets for User-Oriented Fairness in Recommender Systems
by: Liu, Yixiu, et al.
Published: (2025)

EvoDefense: Co-Evolving Black-Box Defense with Large Language Models
by: Li, Yu, et al.
Published: (2026)