Cover Image

DynaTrust: Defending Multi-Agent Systems Against Sleeper Agents via Dynamic Trust Graphs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Li, Yu, Hu, Qiang, Zhang, Yao, Quan, Lili, Yu, Jiongchi, Wang, Junjie
Format:	Preprint
Published:	2026
Subjects:	Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Chimera: Harnessing Multi-Agent LLMs for Automatic Insider Threat Simulation
by: Yu, Jiongchi, et al.
Published: (2025)

A Factor Graph Model of Trust for a Collaborative Multi-Agent System
by: Akbari, Behzad, et al.
Published: (2024)

Trustworthy Agent Network: Trust in Agent Networks Must Be Baked In, Not Bolted On
by: Yao, Yixiang, et al.
Published: (2026)

DynaSearcher: Dynamic Knowledge Graph Augmented Search Agent via Multi-Reward Reinforcement Learning
by: Hao, Chuzhan, et al.
Published: (2025)

PTCBENCH: Benchmarking Contextual Stability of Personality Traits in LLM Systems
by: Yu, Jiongchi, et al.
Published: (2026)

Ev-Trust: An Evolutionarily Stable Trust Mechanism for Decentralized LLM-Based Multi-Agent Service Economies
by: Wang, Jiye, et al.
Published: (2025)

Plant, Persist, Trigger: Sleeper Attack on Large Language Model Agents
by: Li, Yongxiang, et al.
Published: (2026)

SciToolAgent: A Knowledge Graph-Driven Scientific Agent for Multi-Tool Integration
by: Ding, Keyan, et al.
Published: (2025)

Defending LLM-based Multi-Agent Systems Against Cooperative Attacks with Sentence-Level Rectification
by: Luo, Yaoyang, et al.
Published: (2026)

Trust-based Consensus in Multi-Agent Reinforcement Learning Systems
by: Fung, Ho Long, et al.
Published: (2022)

PeerGuard: Defending Multi-Agent Systems Against Backdoor Attacks Through Mutual Reasoning
by: Fan, Falong, et al.
Published: (2025)

Architecting Trust in Artificial Epistemic Agents
by: Marchal, Nahema, et al.
Published: (2026)

Securing GenAI Multi-Agent Systems Against Tool Squatting: A Zero Trust Registry-Based Approach
by: Narajala, Vineeth Sai, et al.
Published: (2025)

DynaDebate: Breaking Homogeneity in Multi-Agent Debate with Dynamic Path Generation
by: Li, Zhenghao, et al.
Published: (2026)

Understanding Individual Agent Importance in Multi-Agent System via Counterfactual Reasoning
by: Chen, Jianming, et al.
Published: (2024)

From Cloud-Native to Trust-Native: A Protocol for Verifiable Multi-Agent Systems
by: Li, Muyang
Published: (2025)

Dynamic Trust-Aware Sparse Communication Topology for LLM-Based Multi-Agent Consensus
by: Gou, Wanshuang, et al.
Published: (2026)

Trusted AI Agents in the Cloud
by: Bodea, Teofil, et al.
Published: (2025)

SuperLocalMemory: Privacy-Preserving Multi-Agent Memory with Bayesian Trust Defense Against Memory Poisoning
by: Bhardwaj, Varun Pratap
Published: (2026)

The Traitors: Deception and Trust in Multi-Agent Language Model Simulations
by: Curvo, Pedro M. P.
Published: (2025)

Multi-Agent Trust Region Policy Optimisation: A Joint Constraint Approach
by: Shek, Chak Lam, et al.
Published: (2025)

TrustAgent: Towards Safe and Trustworthy LLM-based Agents
by: Hua, Wenyue, et al.
Published: (2024)

AgentAsk: Multi-Agent Systems Need to Ask
by: Lin, Bohan, et al.
Published: (2025)

RTBAS: Defending LLM Agents Against Prompt Injection and Privacy Leakage
by: Zhong, Peter Yong, et al.
Published: (2025)

GroupGuard: A Framework for Modeling and Defending Collusive Attacks in Multi-Agent Systems
by: Tao, Yiling, et al.
Published: (2026)

AgentTrap: Measuring Runtime Trust Failures in Third-Party Agent Skills
by: Zhuang, Haomin, et al.
Published: (2026)

Stablecoin Design with Adversarial-Robust Multi-Agent Systems via Trust-Weighted Signal Aggregation
by: You, Shengwei, et al.
Published: (2026)

OpenDeception: Learning Deception and Trust in Human-AI Interaction via Multi-Agent Simulation
by: Wu, Yichen, et al.
Published: (2025)

DynaWeb: Model-Based Reinforcement Learning of Web Agents
by: Ding, Hang, et al.
Published: (2026)

Trusted Routing for Blockchain-Empowered UAV Networks via Multi-Agent Deep Reinforcement Learning
by: Jia, Ziye, et al.
Published: (2025)

ARGUS: Defending LLM Agents Against Context-Aware Prompt Injection
by: Weng, Shihao, et al.
Published: (2026)

DecodingTrust-Agent Platform (DTap): A Controllable and Interactive Red-Teaming Platform for AI Agents
by: Chen, Zhaorun, et al.
Published: (2026)

MOC: Multi-Order Communication in LLM-based Multi-Agent Systems
by: Guan, Yao, et al.
Published: (2026)

VIGIL: Defending LLM Agents Against Tool Stream Injection via Verify-Before-Commit
by: Lin, Junda, et al.
Published: (2026)

OxyGent: Making Multi-Agent Systems Modular, Observable, and Evolvable via Oxy Abstraction
by: Hu, Junxing, et al.
Published: (2026)

TrustUQA: A Trustful Framework for Unified Structured Data Question Answering
by: Zhang, Wen, et al.
Published: (2024)

AutoEmpirical: LLM-Based Automated Research for Empirical Software Fault Analysis
by: Yu, Jiongchi, et al.
Published: (2025)

SoK: Trust-Authorization Mismatch in LLM Agent Interactions
by: Shi, Guanquan, et al.
Published: (2025)

AgentTrust: Runtime Safety Evaluation and Interception for AI Agent Tool Use
by: Yang, Chenglin
Published: (2026)

TrustGLM: Evaluating the Robustness of GraphLLMs Against Prompt, Text, and Structure Attacks
by: Zhang, Qihai, et al.
Published: (2025)