Copertina

The Task Shield: Enforcing Task Alignment to Defend Against Indirect Prompt Injection in LLM Agents

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Jia, Feiran, Wu, Tong, Qin, Xin, Squicciarini, Anna
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Cryptography and Security Artificial Intelligence Computation and Language Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

AgentArmor: Enforcing Program Analysis on Agent Runtime Trace to Defend Against Prompt Injection
di: Wang, Peiran, et al.
Pubblicazione: (2025)

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

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

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

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

Defending Against Alignment-Breaking Attacks via Robustly Aligned LLM
di: Cao, Bochuan, et al.
Pubblicazione: (2023)

Eguard: Defending LLM Embeddings Against Inversion Attacks via Text Mutual Information Optimization
di: Liu, Tiantian, et al.
Pubblicazione: (2024)

VIGIL: Defending LLM Agents Against Tool Stream Injection via Verify-Before-Commit
di: Lin, Junda, et al.
Pubblicazione: (2026)

Jatmo: Prompt Injection Defense by Task-Specific Finetuning
di: Piet, Julien, et al.
Pubblicazione: (2023)

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

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

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

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

A Systematic Literature Review on LLM Defenses Against Prompt Injection and Jailbreaking: Expanding NIST Taxonomy
di: Correia, Pedro H. Barcha, et al.
Pubblicazione: (2026)

When Reject Turns into Accept: Quantifying the Vulnerability of LLM-Based Scientific Reviewers to Indirect Prompt Injection
di: Sahoo, Devanshu, et al.
Pubblicazione: (2025)

Systematically Analyzing Prompt Injection Vulnerabilities in Diverse LLM Architectures
di: Benjamin, Victoria, et al.
Pubblicazione: (2024)

Enhancing Prompt Injection Attacks to LLMs via Poisoning Alignment
di: Shao, Zedian, et al.
Pubblicazione: (2024)

Formalizing and Benchmarking Prompt Injection Attacks and Defenses
di: Liu, Yupei, et al.
Pubblicazione: (2023)

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

Measuring Real-World Prompt Injection Attacks in LLM-based Resume Screening
di: Zhang, Mohan, et al.
Pubblicazione: (2026)

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

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

PIArena: A Platform for Prompt Injection Evaluation
di: Geng, Runpeng, et al.
Pubblicazione: (2026)

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

PISanitizer: Preventing Prompt Injection to Long-Context LLMs via Prompt Sanitization
di: Geng, Runpeng, et al.
Pubblicazione: (2025)

Soft Begging: Modular and Efficient Shielding of LLMs against Prompt Injection and Jailbreaking based on Prompt Tuning
di: Ostermann, Simon, et al.
Pubblicazione: (2024)

WAInjectBench: Benchmarking Prompt Injection Detections for Web Agents
di: Liu, Yinuo, et al.
Pubblicazione: (2025)

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

Manipulating LLM Web Agents with Indirect Prompt Injection Attack via HTML Accessibility Tree
di: Johnson, Sam, et al.
Pubblicazione: (2025)

Overcoming the Retrieval Barrier: Indirect Prompt Injection in the Wild for LLM Systems
di: Chang, Hongyan, et al.
Pubblicazione: (2026)

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

No More, No Less: Task Alignment in Terminal Agents
di: Mavali, Sina, et al.
Pubblicazione: (2026)

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

ICON: Indirect Prompt Injection Defense for Agents based on Inference-Time Correction
di: Wang, Che, et al.
Pubblicazione: (2026)

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

Defending Against Weight-Poisoning Backdoor Attacks for Parameter-Efficient Fine-Tuning
di: Zhao, Shuai, et al.
Pubblicazione: (2024)

Efficient but Vulnerable: Benchmarking and Defending LLM Batch Prompting Attack
di: Yue, Murong, et al.
Pubblicazione: (2025)

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

ReasAlign: Reasoning Enhanced Safety Alignment against Prompt Injection Attack
di: Li, Hao, et al.
Pubblicazione: (2026)

How Not to Detect Prompt Injections with an LLM
di: Choudhary, Sarthak, et al.
Pubblicazione: (2025)