Cover Image

MAGE: Safeguarding LLM Agents against Long-Horizon Threats via Shadow Memory

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wang, Yuhui, Jiang, Tanqiu, Liang, Jiacheng, Fleming, Charles, Wang, Ting
Format:	Preprint
Published:	2026
Subjects:	Cryptography and Security Artificial Intelligence Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

RobustKV: Defending Large Language Models against Jailbreak Attacks via KV Eviction
by: Jiang, Tanqiu, et al.
Published: (2024)

RASA: Routing-Aware Safety Alignment for Mixture-of-Experts Models
by: Liang, Jiacheng, et al.
Published: (2026)

AgentLAB: Benchmarking LLM Agents against Long-Horizon Attacks
by: Jiang, Tanqiu, et al.
Published: (2026)

GraphRAG under Fire
by: Liang, Jiacheng, et al.
Published: (2025)

Shadows in the Code: Exploring the Risks and Defenses of LLM-based Multi-Agent Software Development Systems
by: Wang, Xiaoqing, et al.
Published: (2025)

Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents
by: Yang, Wenkai, et al.
Published: (2024)

Protecting Users From Themselves: Safeguarding Contextual Privacy in Interactions with Conversational Agents
by: Ngong, Ivoline, et al.
Published: (2025)

Reflect-Guard: Enhancing LLM Safeguards against Adversarial Prompts via Logical Self-Reflection
by: Lin, Lixing, et al.
Published: (2026)

Your Agent Can Defend Itself against Backdoor Attacks
by: Changjiang, Li, et al.
Published: (2025)

Covert Malicious Finetuning: Challenges in Safeguarding LLM Adaptation
by: Halawi, Danny, et al.
Published: (2024)

Cross-Modal Content Optimization for Steering Web Agent Preferences
by: Jiang, Tanqiu, et al.
Published: (2025)

BELLS: A Framework Towards Future Proof Benchmarks for the Evaluation of LLM Safeguards
by: Dorn, Diego, et al.
Published: (2024)

SentinelNet: Safeguarding Multi-Agent Collaboration Through Credit-Based Dynamic Threat Detection
by: Feng, Yang, et al.
Published: (2025)

Shadow in the Cache: Unveiling and Mitigating Privacy Risks of KV-cache in LLM Inference
by: Luo, Zhifan, et al.
Published: (2025)

Resource Consumption Threats in Large Language Models
by: Zhang, Yuanhe, et al.
Published: (2026)

Mitigating the Safety-utility Trade-off in LLM Alignment via Adaptive Safe Context Learning
by: Wang, Yanbo, et al.
Published: (2026)

AutoRAN: Automated Hijacking of Safety Reasoning in Large Reasoning Models
by: Liang, Jiacheng, et al.
Published: (2025)

ExCyTIn-Bench: Evaluating LLM agents on Cyber Threat Investigation
by: Wu, Yiran, et al.
Published: (2025)

Topology Matters: Measuring Memory Leakage in Multi-Agent LLMs
by: Liu, Jinbo, et al.
Published: (2025)

Searching for Privacy Risks in LLM Agents via Simulation
by: Zhang, Yanzhe, et al.
Published: (2025)

IP Leakage Attacks Targeting LLM-Based Multi-Agent Systems
by: Wang, Liwen, et al.
Published: (2025)

Stealthy Backdoor Attacks against LLMs Based on Natural Style Triggers
by: Wei, Jiali, et al.
Published: (2026)

The Use of Large Language Models (LLM) for Cyber Threat Intelligence (CTI) in Cybercrime Forums
by: Clairoux-Trepanier, Vanessa, et al.
Published: (2024)

Why Safeguarded Ships Run Aground? Aligned Large Language Models' Safety Mechanisms Tend to Be Anchored in The Template Region
by: Leong, Chak Tou, et al.
Published: (2025)

Quantifying and Defending against Privacy Threats on Federated Knowledge Graph Embedding
by: Hu, Yuke, et al.
Published: (2023)

MIRAGE: Context-Aware Prompt Injection against Mobile GUI Agents via User-Generated Content
by: Guo, Ruoqi, et al.
Published: (2026)

From Threat Intelligence to Firewall Rules: Semantic Relations in Hybrid AI Agent and Expert System Architectures
by: Bonfanti, Chiara, et al.
Published: (2026)

When Agents "Misremember" Collectively: Exploring the Mandela Effect in LLM-based Multi-Agent Systems
by: Xu, Naen, et al.
Published: (2026)

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

ShadowMerge: A Novel Poisoning Attack on Graph-Based Agent Memory via Relation-Channel Conflicts
by: Luo, Yang, et al.
Published: (2026)

SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding
by: Xu, Zhangchen, et al.
Published: (2024)

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

Mobile GUI Agents under Real-world Threats: Are We There Yet?
by: Liu, Guohong, et al.
Published: (2025)

Prompt Injection attack against LLM-integrated Applications
by: Liu, Yi, et al.
Published: (2023)

SIRAJ: Diverse and Efficient Red-Teaming for LLM Agents via Distilled Structured Reasoning
by: Zhou, Kaiwen, et al.
Published: (2025)

SafeSearch: Automated Red-Teaming of LLM-Based Search Agents
by: Dong, Jianshuo, et al.
Published: (2025)

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

Contextualized Privacy Defense for LLM Agents
by: Wen, Yule, et al.
Published: (2026)

Window-based Membership Inference Attacks Against Fine-tuned Large Language Models
by: Chen, Yuetian, et al.
Published: (2026)

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