Copertina

Who Grants the Agent Power? Defending Against Instruction Injection via Task-Centric Access Control

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Cai, Yifeng, Wang, Ziming, Deng, Zhaomeng, Yao, Mengyu, Liu, Junlin, Hu, Yutao, Zhang, Ziqi, Guo, Yao, Li, Ding
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Cryptography and Security
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Who Moved My Transaction? Uncovering Post-Transaction Auditability Vulnerabilities in Modern Super Apps
di: Liu, Junlin, et al.
Pubblicazione: (2025)

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

I Can Tell Your Secrets: Inferring Privacy Attributes from Mini-app Interaction History in Super-apps
di: Cai, Yifeng, et al.
Pubblicazione: (2025)

TEESlice: Protecting Sensitive Neural Network Models in Trusted Execution Environments When Attackers have Pre-Trained Models
di: Li, Ding, et al.
Pubblicazione: (2024)

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

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

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

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

ARGUS: Defending LLM Agents Against Context-Aware Prompt Injection
di: Weng, Shihao, et al.
Pubblicazione: (2026)

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

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

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

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

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

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

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

Moss: Proxy Model-based Full-Weight Aggregation in Federated Learning with Heterogeneous Models
di: Cai, Yifeng, et al.
Pubblicazione: (2025)

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

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

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

Connect the Dots: Knowledge Graph-Guided Crawler Attack on Retrieval-Augmented Generation Systems
di: Yao, Mengyu, et al.
Pubblicazione: (2026)

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

DRIP: Defending Prompt Injection via Token-wise Representation Editing and Residual Instruction Fusion
di: Liu, Ruofan, et al.
Pubblicazione: (2025)

Membership Inference Attacks Against Video Large Language Models
di: Song, Wei, et al.
Pubblicazione: (2026)

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

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

To Defend Against Cyber Attacks, We Must Teach AI Agents to Hack
di: Zhuo, Terry Yue, et al.
Pubblicazione: (2026)

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

TextCrafter: Optimization-Calibrated Noise for Defending Against Text Embedding Inversion
di: Tang, Duoxun, et al.
Pubblicazione: (2025)

Defending Against Neural Network Model Inversion Attacks via Data Poisoning
di: Zhou, Shuai, et al.
Pubblicazione: (2024)

Defending Against Intelligent Attackers at Large Scales
di: Lohn, Andrew J.
Pubblicazione: (2025)

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

Secure Distributed Learning for CAVs: Defending Against Gradient Leakage with Leveled Homomorphic Encryption
di: Najjar, Muhammad Ali, et al.
Pubblicazione: (2025)

Defending Against Attack on the Cloned: In-Band Active Man-in-the-Middle Detection for the Signal Protocol
di: Teng, Wil Liam, et al.
Pubblicazione: (2024)

Temporal UI State Inconsistency in Desktop GUI Agents: Formalizing and Defending Against TOCTOU Attacks on Computer-Use Agents
di: Xu, Wenpeng
Pubblicazione: (2026)

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

Injection Attacks Against End-to-End Encrypted Applications
di: Fábrega, Andrés, et al.
Pubblicazione: (2024)

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

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

WASP: Benchmarking Web Agent Security Against Prompt Injection Attacks
di: Evtimov, Ivan, et al.
Pubblicazione: (2025)