Imagen de Portada

From Storage to Steering: Memory Control Flow Attacks on LLM Agents

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Xu, Zhenlin, Zhu, Xiaogang, Yao, Yu, Xue, Minhui, Song, Yiliao
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

FlowSteer: Prompt-Only Workflow Steering Exposes Planning-Time Vulnerabilities in Multi-Agent LLM Systems
por: Li, Fanxiao, et al.
Publicado: (2026)

Learn What You Want to Unlearn: Unlearning Inversion Attacks against Machine Unlearning
por: Hu, Hongsheng, et al.
Publicado: (2024)

Trust Me, Import This: Dependency Steering Attacks via Malicious Agent Skills
por: Liu, Yiyong, et al.
Publicado: (2026)

Memory Poisoning Attack and Defense on Memory Based LLM-Agents
por: Sunil, Balachandra Devarangadi, et al.
Publicado: (2026)

Bones of Contention: Exploring Query-Efficient Attacks against Skeleton Recognition Systems
por: Cao, Yuxin, et al.
Publicado: (2025)

MalTool: Malicious Tool Attacks on LLM Agents
por: Hu, Yuepeng, et al.
Publicado: (2026)

From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem
por: Mao, Yanxu, et al.
Publicado: (2025)

Private Synthetic Data Generation in Bounded Memory
por: Holland, Rayne, et al.
Publicado: (2024)

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

Black-Box Skill Stealing Attack from Proprietary LLM Agents: An Empirical Study
por: Wang, Zihan, et al.
Publicado: (2026)

Evolving Skill-Structured Attack Memory Enhances LLM Jailbreaking
por: Zhang, Junke, et al.
Publicado: (2026)

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

Steering in the Shadows: Causal Amplification for Activation Space Attacks in Large Language Models
por: Xu, Zhiyuan, et al.
Publicado: (2025)

Red-Teaming LLM Multi-Agent Systems via Communication Attacks
por: He, Pengfei, et al.
Publicado: (2025)

Harmless Yet Harmful: Neutral Prompting Attacks for Stealthy Hallucination Steering in Agent Skills
por: Hsu, Chia-Yi, et al.
Publicado: (2026)

Collaborative Shadows: Distributed Backdoor Attacks in LLM-Based Multi-Agent Systems
por: Zhu, Pengyu, et al.
Publicado: (2025)

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

Your Agent Is Mine: Measuring Malicious Intermediary Attacks on the LLM Supply Chain
por: Liu, Hanzhi, et al.
Publicado: (2026)

AgentRAE: Remote Action Execution through Notification-based Visual Backdoors against Screenshots-based Mobile GUI Agents
por: Luo, Yutao, et al.
Publicado: (2026)

Ghost in the Agent: Redefining Information Flow Tracking for LLM Agents
por: Cai, Yuandao, et al.
Publicado: (2026)

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

Towards Strengthening Deep Learning-based Side Channel Attacks with Mixup
por: Luo, Zhimin, et al.
Publicado: (2021)

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

From LLMs to Agents: A Comparative Evaluation of LLMs and LLM-based Agents in Security Patch Detection
por: Han, Junxiao, et al.
Publicado: (2025)

DrunkAgent: Stealthy Memory Corruption in LLM-Powered Recommender Agents
por: Yang, Shiyi, et al.
Publicado: (2025)

Adversarial Attacks on Reinforcement Learning Agents for Command and Control
por: Dabholkar, Ahaan, et al.
Publicado: (2024)

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

Observable Channels, Not Just Storage: Evaluating Privacy Leakage in LLM Agent Pipelines
por: Huang, Tao, et al.
Publicado: (2026)

SoK: The Security-Safety Continuum of Multimodal Foundation Models through Information Flow and Global Game-Theoretic Analysis of Asymmetric Threats
por: Sun, Ruoxi, et al.
Publicado: (2024)

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

MemoPhishAgent: Memory-Augmented Multi-Modal LLM Agent for Phishing URL Detection
por: Chen, Xuan, et al.
Publicado: (2026)

The Invisible Game on the Internet: A Case Study of Decoding Deceptive Patterns
por: Shi, Zewei, et al.
Publicado: (2024)

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

Enhancing LLM-based Autonomous Driving Agents to Mitigate Perception Attacks
por: Song, Ruoyu, et al.
Publicado: (2024)

MRMMIA: Membership Inference Attacks on Memory in Chat Agents
por: Chen, Kai, et al.
Publicado: (2026)

CyberSleuth: Autonomous Blue-Team LLM Agent for Web Attack Forensics
por: Fumero, Stefano, 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)

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

Securing LLM Agents Need Intent-to-Execution Integrity
por: Qu, Wenjie, et al.
Publicado: (2026)

AttackLLM: LLM-based Attack Pattern Generation for an Industrial Control System
por: Ahmed, Chuadhry Mujeeb
Publicado: (2025)