Image de couverture de livre

Zombie Agents: Persistent Control of Self-Evolving LLM Agents via Self-Reinforcing Injections

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Yang, Xianglin, He, Yufei, Ji, Shuo, Hooi, Bryan, Dong, Jin Song
Format:	Preprint
Publié:	2026
Sujets:	Cryptography and Security Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Turning Bias into Bugs: Bandit-Guided Style Manipulation Attacks on LLM Judges
par: Yang, Xianglin, et autres
Publié: (2026)

WARD: Adversarially Robust Defense of Web Agents Against Prompt Injections
par: Cao, Tri, et autres
Publié: (2026)

VPI-Bench: Visual Prompt Injection Attacks for Computer-Use Agents
par: Cao, Tri, et autres
Publié: (2025)

Proteus: A Self-Evolving Red Team for Agent Skill Ecosystems
par: Zhou, Zhaojiacheng
Publié: (2026)

OEP: Poisoning Self-Evolving LLM Agents via Locally Correct but Non-Transferable Experiences
par: Wang, Kaixiang, et autres
Publié: (2026)

AgentVigil: Generic Black-Box Red-teaming for Indirect Prompt Injection against LLM Agents
par: Wang, Zhun, et autres
Publié: (2025)

MemoryGraft: Persistent Compromise of LLM Agents via Poisoned Experience Retrieval
par: Srivastava, Saksham Sahai, et autres
Publié: (2025)

VIGIL: Defending LLM Agents Against Tool Stream Injection via Verify-Before-Commit
par: Lin, Junda, et autres
Publié: (2026)

Manipulating LLM Web Agents with Indirect Prompt Injection Attack via HTML Accessibility Tree
par: Johnson, Sam, et autres
Publié: (2025)

AgentTypo: Adaptive Typographic Prompt Injection Attacks against Black-box Multimodal Agents
par: Li, Yanjie, et autres
Publié: (2025)

RTBAS: Defending LLM Agents Against Prompt Injection and Privacy Leakage
par: Zhong, Peter Yong, et autres
Publié: (2025)

To Protect the LLM Agent Against the Prompt Injection Attack with Polymorphic Prompt
par: Wang, Zhilong, et autres
Publié: (2025)

ICON: Indirect Prompt Injection Defense for Agents based on Inference-Time Correction
par: Wang, Che, et autres
Publié: (2026)

LLM-enabled Applications Require System-Level Threat Monitoring
par: Zhang, Yedi, et autres
Publié: (2026)

Enhancing Model Defense Against Jailbreaks with Proactive Safety Reasoning
par: Yang, Xianglin, et autres
Publié: (2025)

ASPI: Seeking Ambiguity Clarification Amplifies Prompt Injection Vulnerability in LLM Agents
par: Sehwag, Udari Madhushani, et autres
Publié: (2026)

DRIFT: Dynamic Rule-Based Defense with Injection Isolation for Securing LLM Agents
par: Li, Hao, et autres
Publié: (2025)

AIRGuard: Guarding Agent Actions with Runtime Authority Control
par: Qin, Suliu, et autres
Publié: (2026)

From Prompt Injections to Protocol Exploits: Threats in LLM-Powered AI Agents Workflows
par: Ferrag, Mohamed Amine, et autres
Publié: (2025)

CheatAgent: Attacking LLM-Empowered Recommender Systems via LLM Agent
par: Ning, Liang-bo, et autres
Publié: (2025)

A Framework for Formalizing LLM Agent Security
par: Siu, Vincent, et autres
Publié: (2026)

CyberEvolver: Structured Self-Evolution for Cybersecurity Agents On the Fly
par: Fan, Yihe, et autres
Publié: (2026)

Omission Constraints Decay While Commission Constraints Persist in Long-Context LLM Agents
par: Gamage, Yeran
Publié: (2026)

Agent-Sentry: Bounding LLM Agents via Execution Provenance
par: Sequeira, Rohan, et autres
Publié: (2026)

WebAgentGuard: A Reasoning-Driven Guard Model for Detecting Prompt Injection Attacks in Web Agents
par: Chen, Yulin, et autres
Publié: (2026)

DRIP: Defending Prompt Injection via Token-wise Representation Editing and Residual Instruction Fusion
par: Liu, Ruofan, et autres
Publié: (2025)

MELON: Provable Defense Against Indirect Prompt Injection Attacks in AI Agents
par: Zhu, Kaijie, et autres
Publié: (2025)

Progent: Securing AI Agents with Privilege Control
par: Shi, Tianneng, et autres
Publié: (2025)

Silent Egress: When Implicit Prompt Injection Makes LLM Agents Leak Without a Trace
par: Lan, Qianlong, et autres
Publié: (2026)

Securing AI Agents Against Prompt Injection Attacks
par: Ramakrishnan, Badrinath, et autres
Publié: (2025)

Agent Safety Alignment via Reinforcement Learning
par: Sha, Zeyang, et autres
Publié: (2025)

GhostEI-Bench: Do Mobile Agents Resilience to Environmental Injection in Dynamic On-Device Environments?
par: Chen, Chiyu, et autres
Publié: (2025)

Unveiling Privacy Risks in LLM Agent Memory
par: Wang, Bo, et autres
Publié: (2025)

Whispers of Wealth: Red-Teaming Google's Agent Payments Protocol via Prompt Injection
par: Debi, Tanusree, et autres
Publié: (2026)

A Vision for Access Control in LLM-based Agent Systems
par: Li, Xinfeng, et autres
Publié: (2025)

Prompt Infection: LLM-to-LLM Prompt Injection within Multi-Agent Systems
par: Lee, Donghyun, et autres
Publié: (2024)

ClawGuard: A Runtime Security Framework for Tool-Augmented LLM Agents Against Indirect Prompt Injection
par: Zhao, Wei, et autres
Publié: (2026)

FlipAttack: Jailbreak LLMs via Flipping
par: Liu, Yue, et autres
Publié: (2024)

OpenSage: Self-programming Agent Generation Engine
par: Li, Hongwei, et autres
Publié: (2026)

GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning
par: Liu, Yue, et autres
Publié: (2025)