Imagen de Portada

AgentSys: Secure and Dynamic LLM Agents Through Explicit Hierarchical Memory Management

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Wen, Ruoyao, Li, Hao, Xiao, Chaowei, Zhang, Ning
Formato:	Preprint
Publicado:	2026
Materias:	Cryptography and Security Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

DRIFT: Dynamic Rule-Based Defense with Injection Isolation for Securing LLM Agents
por: Li, Hao, et al.
Publicado: (2025)

AgentDyn: Are Your Agent Security Defenses Deployable in Real-World Dynamic Environments?
por: Li, Hao, et al.
Publicado: (2026)

A New Era in LLM Security: Exploring Security Concerns in Real-World LLM-based Systems
por: Wu, Fangzhou, et al.
Publicado: (2024)

WIPI: A New Web Threat for LLM-Driven Web Agents
por: Wu, Fangzhou, et al.
Publicado: (2024)

SafeHarbor: Hierarchical Memory-Augmented Guardrail for LLM Agent Safety
por: Liu, Zhe, et al.
Publicado: (2026)

LLM Agents Should Employ Security Principles
por: Zhang, Kaiyuan, et al.
Publicado: (2025)

CheatAgent: Attacking LLM-Empowered Recommender Systems via LLM Agent
por: Ning, Liang-bo, et al.
Publicado: (2025)

From Thinker to Society: Security in Hierarchical Autonomy Evolution of AI Agents
por: Zhang, Xiaolei, et al.
Publicado: (2026)

Agent Audit: A Security Analysis System for LLM Agent Applications
por: Zhang, Haiyue, et al.
Publicado: (2026)

Architecting Secure AI Agents: Perspectives on System-Level Defenses Against Indirect Prompt Injection Attacks
por: Xiang, Chong, et al.
Publicado: (2026)

SkCC: Portable and Secure Skill Compilation for Cross-Framework LLM Agents
por: Ouyang, Yipeng, et al.
Publicado: (2026)

AgentWard: A Lifecycle Security Architecture for Autonomous AI Agents
por: Zhang, Yixiang, et al.
Publicado: (2026)

Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents
por: Zhang, Hanrong, et al.
Publicado: (2024)

Security of AI Agents
por: He, Yifeng, et al.
Publicado: (2024)

SafeHarness: Lifecycle-Integrated Security Architecture for LLM-based Agent Deployment
por: Lin, Xixun, et al.
Publicado: (2026)

A Framework for Formalizing LLM Agent Security
por: Siu, Vincent, et al.
Publicado: (2026)

Unveiling Privacy Risks in LLM Agent Memory
por: Wang, Bo, et al.
Publicado: (2025)

Taming OpenClaw: Security Analysis and Mitigation of Autonomous LLM Agent Threats
por: Deng, Xinhao, et al.
Publicado: (2026)

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

MCP Security Bench (MSB): Benchmarking Attacks Against Model Context Protocol in LLM Agents
por: Zhang, Dongsen, et al.
Publicado: (2025)

DemonAgent: Dynamically Encrypted Multi-Backdoor Implantation Attack on LLM-based Agent
por: Zhu, Pengyu, et al.
Publicado: (2025)

MemLineage: Lineage-Guided Enforcement for LLM Agent Memory
por: Ouyang, Ciyan, et al.
Publicado: (2026)

Hijacking Agent Memory: Stealthy Trojan Attacks Through Conversational Interaction
por: Wang, Hongtao, et al.
Publicado: (2026)

Provably Secure Agent Guardrail
por: Wu, Benlong, et al.
Publicado: (2026)

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

Credential Leakage in LLM Agent Skills: A Large-Scale Empirical Study
por: Chen, Zhihao, et al.
Publicado: (2026)

AutoPentest: Enhancing Vulnerability Management With Autonomous LLM Agents
por: Henke, Julius
Publicado: (2025)

Structured Security Auditing and Robustness Enhancement for Untrusted Agent Skills
por: Lv, Lijia, et al.
Publicado: (2026)

ADAM: A Systematic Data Extraction Attack on Agent Memory via Adaptive Querying
por: Lyu, Xingyu, et al.
Publicado: (2026)

Breaking the Code: Security Assessment of AI Code Agents Through Systematic Jailbreaking Attacks
por: Saha, Shoumik, et al.
Publicado: (2025)

The Granularity Mismatch in Agent Security: Argument-Level Provenance Solves Enforcement and Isolates the LLM Reasoning Bottleneck
por: Fan, Linfeng, et al.
Publicado: (2026)

JailDAM: Jailbreak Detection with Adaptive Memory for Vision-Language Model
por: Nian, Yi, et al.
Publicado: (2025)

AutoDAN-Reasoning: Enhancing Strategies Exploration based Jailbreak Attacks with Test-Time Scaling
por: Liu, Xiaogeng, et al.
Publicado: (2025)

A Comparative Evaluation of AI Agent Security Guardrails
por: Li, Qi, et al.
Publicado: (2026)

Targeted Bit-Flip Attacks on LLM-Based Agents
por: Wang, Jialai, et al.
Publicado: (2026)

Towards Secure Agent Skills: Architecture, Threat Taxonomy, and Security Analysis
por: Li, Zhiyuan, et al.
Publicado: (2026)

ReasAlign: Reasoning Enhanced Safety Alignment against Prompt Injection Attack
por: Li, Hao, et al.
Publicado: (2026)

LPG: Balancing Efficiency and Policy Reasoning in Latent Policy Guardrails
por: Li, Nanxi, et al.
Publicado: (2026)

Progent: Securing AI Agents with Privilege Control
por: Shi, Tianneng, et al.
Publicado: (2025)

Securing LLM-Generated Embedded Firmware through AI Agent-Driven Validation and Patching
por: Abtahi, Seyed Moein, et al.
Publicado: (2025)