Imagen de Portada

Attention is All You Need to Defend Against Indirect Prompt Injection Attacks in LLMs

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Zhong, Yinan, Miao, Qianhao, Chen, Yanjiao, Deng, Jiangyi, Cheng, Yushi, Xu, Wenyuan
Formato:	Preprint
Publicado:	2025
Materias:	Cryptography and Security
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

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

Defending Against Indirect Prompt Injection Attacks With Spotlighting
por: Hines, Keegan, et al.
Publicado: (2024)

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

Lessons from Defending Gemini Against Indirect Prompt Injections
por: Shi, Chongyang, et al.
Publicado: (2025)

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

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

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

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

StruQ: Defending Against Prompt Injection with Structured Queries
por: Chen, Sizhe, et al.
Publicado: (2024)

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

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

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

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

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

RTBAS: Defending LLM Agents Against Prompt Injection and Privacy Leakage
por: Zhong, Peter Yong, et al.
Publicado: (2025)

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

GenTel-Safe: A Unified Benchmark and Shielding Framework for Defending Against Prompt Injection Attacks
por: Li, Rongchang, et al.
Publicado: (2024)

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

SecAlign: Defending Against Prompt Injection with Preference Optimization
por: Chen, Sizhe, et al.
Publicado: (2024)

Analysis of LLMs Against Prompt Injection and Jailbreak Attacks
por: Jaiswal, Piyush, et al.
Publicado: (2026)

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

MUZZLE: Adaptive Agentic Red-Teaming of Web Agents Against Indirect Prompt Injection Attacks
por: Syros, Georgios, et al.
Publicado: (2026)

Robustness via Referencing: Defending against Prompt Injection Attacks by Referencing the Executed Instruction
por: Chen, Yulin, et al.
Publicado: (2025)

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

The Task Shield: Enforcing Task Alignment to Defend Against Indirect Prompt Injection in LLM Agents
por: Jia, Feiran, et al.
Publicado: (2024)

Patronus: Safeguarding Text-to-Image Models against White-Box Adversaries
por: Li, Xinfeng, et al.
Publicado: (2025)

ARGUS: Defending LLM Agents Against Context-Aware Prompt Injection
por: Weng, Shihao, 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)

Attention Tracker: Detecting Prompt Injection Attacks in LLMs
por: Hung, Kuo-Han, et al.
Publicado: (2024)

Buffer is All You Need: Defending Federated Learning against Backdoor Attacks under Non-iids via Buffering
por: Lyu, Xingyu, et al.
Publicado: (2025)

Is Your Prompt Safe? Investigating Prompt Injection Attacks Against Open-Source LLMs
por: Wang, Jiawen, et al.
Publicado: (2025)

Adversarial Tuning: Defending Against Jailbreak Attacks for LLMs
por: Liu, Fan, et al.
Publicado: (2024)

Invitation Is All You Need! Promptware Attacks Against LLM-Powered Assistants in Production Are Practical and Dangerous
por: Nassi, Ben, et al.
Publicado: (2025)

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

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

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

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

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

Strengthening Polymorphic Prompt Assembling: Dynamic Separator Generation Against Emerging Prompt Injection Attacks
por: Dorzhiev, Nima, et al.
Publicado: (2026)

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