Imagen de Portada

Sleeper Channels and Provenance Gates: Persistent Prompt Injection in Always-on Autonomous AI Agents

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Maloyan, Narek, Namiot, Dmitry
Formato:	Preprint
Publicado:	2026
Materias:	Cryptography and Security
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Prompt Injection Attacks on Agentic Coding Assistants: A Systematic Analysis of Vulnerabilities in Skills, Tools, and Protocol Ecosystems
por: Maloyan, Narek, et al.
Publicado: (2026)

Breaking the Protocol: Security Analysis of the Model Context Protocol Specification and Prompt Injection Vulnerabilities in Tool-Integrated LLM Agents
por: Maloyan, Narek, et al.
Publicado: (2026)

Adversarial Attacks on LLM-as-a-Judge Systems: Insights from Prompt Injections
por: Maloyan, Narek, et al.
Publicado: (2025)

Investigating the Vulnerability of LLM-as-a-Judge Architectures to Prompt-Injection Attacks
por: Maloyan, Narek, et al.
Publicado: (2025)

AI Agents May Always Fall for Prompt Injections
por: Abdelnabi, Sahar, et al.
Publicado: (2026)

AegisAgent: An Autonomous Defense Agent Against Prompt Injection Attacks in LLM-HARs
por: Wang, Yihan, et al.
Publicado: (2025)

Cross-Scale Persistence Analysis of EM Side-Channels for Reference-Free Detection of Always-On Hardware Trojans
por: Tahghigh, Mahsa, et al.
Publicado: (2026)

Securing AI Agents Against Prompt Injection Attacks
por: Ramakrishnan, Badrinath, et al.
Publicado: (2025)

Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training
por: Hubinger, Evan, et al.
Publicado: (2024)

Cybersecurity AI: Hacking the AI Hackers via Prompt Injection
por: Mayoral-Vilches, Víctor, et al.
Publicado: (2025)

PINA: Prompt Injection Attack against Navigation Agents
por: Liu, Jiani, et al.
Publicado: (2026)

Prompt Injection Attack to Tool Selection in LLM Agents
por: Shi, Jiawen, et al.
Publicado: (2025)

ObliInjection: Order-Oblivious Prompt Injection Attack to LLM Agents with Multi-source Data
por: Wang, Reachal, et al.
Publicado: (2025)

AgentWatcher: A Rule-based Prompt Injection Monitor
por: Wang, Yanting, et al.
Publicado: (2026)

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

AgentVisor: Defending LLM Agents Against Prompt Injection via Semantic Virtualization
por: Ying, Zonghao, et al.
Publicado: (2026)

MELON: Provable Defense Against Indirect Prompt Injection Attacks in AI Agents
por: Zhu, Kaijie, et al.
Publicado: (2025)

From Prompt Injections to Protocol Exploits: Threats in LLM-Powered AI Agents Workflows
por: Ferrag, Mohamed Amine, et al.
Publicado: (2025)

To Protect the LLM Agent Against the Prompt Injection Attack with Polymorphic Prompt
por: Wang, Zhilong, et al.
Publicado: (2025)

PromptShield: Deployable Detection for Prompt Injection Attacks
por: Jacob, Dennis, et al.
Publicado: (2025)

System Prompt Poisoning: Persistent Attacks on Large Language Models Beyond User Injection
por: Li, Zongze, et al.
Publicado: (2025)

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

LogJack: Indirect Prompt Injection Through Cloud Logs Against LLM Debugging Agents
por: Shah, Harsh
Publicado: (2026)

MAD-Spear: A Conformity-Driven Prompt Injection Attack on Multi-Agent Debate Systems
por: Cui, Yu, et al.
Publicado: (2025)

Are AI-assisted Development Tools Immune to Prompt Injection?
por: Huang, Charoes, et al.
Publicado: (2026)

Prompt Injection 2.0: Hybrid AI Threats
por: McHugh, Jeremy, et al.
Publicado: (2025)

Zombie Agents: Persistent Control of Self-Evolving LLM Agents via Self-Reinforcing Injections
por: Yang, Xianglin, 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)

PromptSleuth: Detecting Prompt Injection via Semantic Intent Invariance
por: Wang, Mengxiao, et al.
Publicado: (2025)

Dual-Guard: Dual-Channel Latent Watermarking for Provenance and Tamper Localization in Diffusion Images
por: Xie, JinFeng, et al.
Publicado: (2026)

The Vulnerability of LLM Rankers to Prompt Injection Attacks
por: Yin, Yu, et al.
Publicado: (2026)

Design Patterns for Securing LLM Agents against Prompt Injections
por: Beurer-Kellner, Luca, et al.
Publicado: (2025)

Defending Against Prompt Injection with DataFilter
por: Wang, Yizhu, et al.
Publicado: (2025)

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

PlanGuard: Defending Agents against Indirect Prompt Injection via Planning-based Consistency Verification
por: Gong, Guangyu, et al.
Publicado: (2026)

Agentic AI for Autonomous Defense in Software Supply Chain Security: Beyond Provenance to Vulnerability Mitigation
por: Syed, Toqeer Ali, et al.
Publicado: (2025)

BrowseSafe: Understanding and Preventing Prompt Injection Within AI Browser Agents
por: Zhang, Kaiyuan, et al.
Publicado: (2025)

IPI-proxy: An Intercepting Proxy for Red-Teaming Web-Browsing AI Agents Against Indirect Prompt Injection
por: Chia-Pei, et al.
Publicado: (2026)

How Vulnerable Are AI Agents to Indirect Prompt Injections? Insights from a Large-Scale Public Competition
por: Dziemian, Mateusz, et al.
Publicado: (2026)

The Agent Economy: A Blockchain-Based Foundation for Autonomous AI Agents
por: Xu, Minghui
Publicado: (2026)