ICON: Indirect Prompt Injection Defense for Agents based on Inference-Time Correction

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wang, Che, Zhang, Fuyao, Zhang, Jiaming, Zhang, Ziqi, Wang, Yinghui, Huang, Longtao, Gao, Jianbo, Chen, Zhong, Lim, Wei Yang Bryan
Format:	Preprint
Published:	2026
Subjects:	Artificial Intelligence Cryptography and Security
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

AdapTools: Adaptive Tool-based Indirect Prompt Injection Attacks on Agentic LLMs
by: Wang, Che, et al.
Published: (2026)

DualTAP: A Dual-Task Adversarial Protector for Mobile MLLM Agents
by: Zhang, Fuyao, et al.
Published: (2025)

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

VENOMREC: Cross-Modal Interactive Poisoning for Targeted Promotion in Multimodal LLM Recommender Systems
by: Guan, Guowei, et al.
Published: (2026)

FATH: Authentication-based Test-time Defense against Indirect Prompt Injection Attacks
by: Wang, Jiongxiao, et al.
Published: (2024)

QueryIPI: Query-agnostic Indirect Prompt Injection on Coding Agents
by: Xie, Yuchong, et al.
Published: (2025)

Adaptive Attacks Break Defenses Against Indirect Prompt Injection Attacks on LLM Agents
by: Zhan, Qiusi, et al.
Published: (2025)

Can Indirect Prompt Injection Attacks Be Detected and Removed?
by: Chen, Yulin, et al.
Published: (2025)

TopicAttack: An Indirect Prompt Injection Attack via Topic Transition
by: Chen, Yulin, et al.
Published: (2025)

System-Level Defense against Indirect Prompt Injection Attacks: An Information Flow Control Perspective
by: Wu, Fangzhou, et al.
Published: (2024)

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

Indirect Prompt Injection in the Wild: An Empirical Study of Prevalence, Techniques, and Objectives
by: Khodayari, Soheil, et al.
Published: (2026)

Backdoor-Powered Prompt Injection Attacks Nullify Defense Methods
by: Chen, Yulin, et al.
Published: (2025)

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

IPIGuard: A Novel Tool Dependency Graph-Based Defense Against Indirect Prompt Injection in LLM Agents
by: An, Hengyu, et al.
Published: (2025)

Defense Against Prompt Injection Attack by Leveraging Attack Techniques
by: Chen, Yulin, et al.
Published: (2024)

Hidden-in-Plain-Text: A Benchmark for Social-Web Indirect Prompt Injection in RAG
by: Guo, Haoze, et al.
Published: (2026)

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

WARD: Adversarially Robust Defense of Web Agents Against Prompt Injections
by: Cao, Tri, et al.
Published: (2026)

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

Attention is All You Need to Defend Against Indirect Prompt Injection Attacks in LLMs
by: Zhong, Yinan, et al.
Published: (2025)

AgentVigil: Generic Black-Box Red-teaming for Indirect Prompt Injection against LLM Agents
by: Wang, Zhun, et al.
Published: (2025)

Defending Against Prompt Injection With a Few DefensiveTokens
by: Chen, Sizhe, et al.
Published: (2025)

VortexPIA: Indirect Prompt Injection Attack against LLMs for Efficient Extraction of User Privacy
by: Cui, Yu, et al.
Published: (2025)

The Cognitive Firewall:Securing Browser Based AI Agents Against Indirect Prompt Injection Via Hybrid Edge Cloud Defense
by: Lan, Qianlong, et al.
Published: (2026)

AgentDojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents
by: Debenedetti, Edoardo, et al.
Published: (2024)

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

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

Defending against Indirect Prompt Injection by Instruction Detection
by: Wen, Tongyu, et al.
Published: (2025)

ARGUS: Defending Against Multimodal Indirect Prompt Injection via Steering Instruction-Following Behavior
by: Lu, Weikai, et al.
Published: (2025)

PISmith: Reinforcement Learning-based Red Teaming for Prompt Injection Defenses
by: Yin, Chenlong, et al.
Published: (2026)

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

PromptArmor: Simple yet Effective Prompt Injection Defenses
by: Shi, Tianneng, et al.
Published: (2025)

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

LivePI: More Realistic Benchmarking of Agents Against Indirect Prompt Injection
by: Zhao, Lei, et al.
Published: (2026)

Indirect Prompt Injections: Are Firewalls All You Need, or Stronger Benchmarks?
by: Bhagwatkar, Rishika, et al.
Published: (2025)

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

Verifiably Forgotten? Gradient Differences Still Enable Data Reconstruction in Federated Unlearning
by: Zhang, Fuyao, et al.
Published: (2025)

InjecAgent: Benchmarking Indirect Prompt Injections in Tool-Integrated Large Language Model Agents
by: Zhan, Qiusi, et al.
Published: (2024)

Dynamic Probabilistic Noise Injection for Membership Inference Defense
by: Forough, Javad, et al.
Published: (2025)