Copertina

MindGuard: Intrinsic Decision Inspection for Securing LLM Agents Against Metadata Poisoning

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Wang, Zhiqiang, Du, Haohua, Shi, Guanquan, Zhang, Junyang, Cheng, HaoRan, Yao, Yunhao, Guo, Kaiwen, Li, Xiang-Yang
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Cryptography and Security
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

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

MCPTox: A Benchmark for Tool Poisoning Attack on Real-World MCP Servers
di: Wang, Zhiqiang, et al.
Pubblicazione: (2025)

SECNEURON: Reliable and Flexible Abuse Control in Local LLMs via Hybrid Neuron Encryption
di: Wang, Zhiqiang, et al.
Pubblicazione: (2025)

MCP-ITP: An Automated Framework for Implicit Tool Poisoning in MCP
di: Li, Ruiqi, et al.
Pubblicazione: (2026)

RouteGuard: Internal-Signal Detection of Skill Poisoning in LLM Agents
di: Xiao, Wenjie, et al.
Pubblicazione: (2026)

Securing Voice Authentication Applications Against Targeted Data Poisoning
di: Mohammadi, Alireza, et al.
Pubblicazione: (2024)

ClawGuard: A Runtime Security Framework for Tool-Augmented LLM Agents Against Indirect Prompt Injection
di: Zhao, Wei, et al.
Pubblicazione: (2026)

LLM Security Guard for Code
di: Kavian, Arya, et al.
Pubblicazione: (2024)

RemoteRAG: A Privacy-Preserving LLM Cloud RAG Service
di: Cheng, Yihang, et al.
Pubblicazione: (2024)

IntentMiner: Intent Inversion Attack via Tool Call Analysis in the Model Context Protocol
di: Yao, Yunhao, et al.
Pubblicazione: (2025)

TransLinkGuard: Safeguarding Transformer Models Against Model Stealing in Edge Deployment
di: Li, Qinfeng, et al.
Pubblicazione: (2024)

CircuitGuard: Mitigating LLM Memorization in RTL Code Generation Against IP Leakage
di: Mashnoor, Nowfel, et al.
Pubblicazione: (2025)

AgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge Bases
di: Chen, Zhaorun, et al.
Pubblicazione: (2024)

AttriGuard: Defeating Indirect Prompt Injection in LLM Agents via Causal Attribution of Tool Invocations
di: He, Yu, et al.
Pubblicazione: (2026)

Poisoning the Watchtower: Prompt Injection Attacks Against LLM-Augmented Security Operations Through Adversarial Log Content
di: Pandey, Rohan, et al.
Pubblicazione: (2026)

WAFBOOSTER: Automatic Boosting of WAF Security Against Mutated Malicious Payloads
di: Wu, Cong, et al.
Pubblicazione: (2025)

A-MemGuard: A Proactive Defense Framework for LLM-Based Agent Memory
di: Wei, Qianshan, et al.
Pubblicazione: (2025)

LLMGuard: Guarding Against Unsafe LLM Behavior
di: Goyal, Shubh, et al.
Pubblicazione: (2024)

AgentGuard: An Attribute-Based Access Control Framework for Tool-Use LLM-Based Agent
di: Luo, Jiaqi, et al.
Pubblicazione: (2026)

Supply-Chain Poisoning Attacks Against LLM Coding Agent Skill Ecosystems
di: Qu, Yubin, et al.
Pubblicazione: (2026)

AgentGuard: A Multi-Agent Framework for Robust Package Confusion Detection via Hybrid Search and Metadata-Content Fusion
di: Li, Yu, et al.
Pubblicazione: (2026)

Hidden in the Metadata: Stealth Poisoning Attacks on Multimodal Retrieval-Augmented Generation
di: Edemacu, Kennedy, et al.
Pubblicazione: (2026)

Control at Stake: Evaluating the Security Landscape of LLM-Driven Email Agents
di: Wu, Jiangrong, et al.
Pubblicazione: (2025)

PVMark: Enabling Public Verifiability for LLM Watermarking Schemes
di: Duan, Haohua, et al.
Pubblicazione: (2025)

WebAgentGuard: A Reasoning-Driven Guard Model for Detecting Prompt Injection Attacks in Web Agents
di: Chen, Yulin, et al.
Pubblicazione: (2026)

Robustness of Locally Differentially Private Graph Analysis Against Poisoning
di: Imola, Jacob, et al.
Pubblicazione: (2022)

Mind the Web: The Security of Web Use Agents
di: Shapira, Avishag, et al.
Pubblicazione: (2025)

LoopTrap: Termination Poisoning Attacks on LLM Agents
di: Xu, Huiyu, et al.
Pubblicazione: (2026)

SleeperNets: Universal Backdoor Poisoning Attacks Against Reinforcement Learning Agents
di: Rathbun, Ethan, et al.
Pubblicazione: (2024)

SecureLearn -- An Attack-agnostic Defense for Multiclass Machine Learning Against Data Poisoning Attacks
di: Paracha, Anum, et al.
Pubblicazione: (2025)

Confused ChatGPT: Cross-App Context Poisoning via First-Party APIs
di: Wang, Chao, et al.
Pubblicazione: (2026)

Sentra-Guard: A Real-Time Multilingual Defense Against Adversarial LLM Prompts
di: Hasan, Md. Mehedi, et al.
Pubblicazione: (2025)

BraveGuard: From Open-World Threats to Safer Computer-Use Agents
di: Feng, Yunhao, et al.
Pubblicazione: (2026)

Timber! Poisoning Decision Trees
di: Calzavara, Stefano, et al.
Pubblicazione: (2024)

Poison Attacks and Adversarial Prompts Against an Informed University Virtual Assistant
di: Fernandez, Ivan A., et al.
Pubblicazione: (2024)

Activation Gradient based Poisoned Sample Detection Against Backdoor Attacks
di: Yuan, Danni, et al.
Pubblicazione: (2023)

DistillGuard: Evaluating Defenses Against LLM Knowledge Distillation
di: Jiang, Bo
Pubblicazione: (2026)

ProtoGuard-SL: Prototype Consistency Based Backdoor Defense for Vertical Split Learning
di: Shui, Yuhan, et al.
Pubblicazione: (2026)

ClawGuard: Out-of-Band Detection of LLM Agent Workflow Hijacking via EM Side Channel
di: Gan, Leo Linqian, et al.
Pubblicazione: (2026)

Reframing LLM Agent Security as an Agent-Human Interaction Problem
di: Wang, Peiran, et al.
Pubblicazione: (2026)