Image de couverture de livre

AgentSentry: Mitigating Indirect Prompt Injection in LLM Agents via Temporal Causal Diagnostics and Context Purification

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Zhang, Tian, Xu, Yiwei, Wang, Juan, Guo, Keyan, Xu, Xiaoyang, Xiao, Bowen, Guan, Quanlong, Fan, Jinlin, Liu, Jiawei, Liu, Zhiquan, Hu, Hongxin
Format:	Preprint
Publié:	2026
Sujets:	Cryptography and Security Artificial Intelligence D.4.6; K.6.5; I.2.7
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Depth-Dependent Indirect Prompt Injection in Tool-Calling ReAct Agents: Injection Depth, Payload Framing, and Turn-Budget Sensitivity
par: Rashidi, Mohammadreza
Publié: (2026)

Multi-Agent Honeypot-Based Request-Response Context Dataset for Improved SQL Injection Detection Performance
par: Yu, Hao, et autres
Publié: (2026)

Benchmarking Autonomous Agents against Temporal, Spatial, and Semantic Evasions
par: Ma, Jianan, et autres
Publié: (2026)

Refusal Evaluation in Coding LLMs and Code Agents: A Systematic Review of Thirteen Malicious-Code Prompt Corpora (2023-2025)
par: Young, Richard J., et autres
Publié: (2026)

A Framework for Assessing AI Agent Decisions and Outcomes in AutoML Pipelines
par: Du, Gaoyuan, et autres
Publié: (2026)

DEpiABS: Differentiable Epidemic Agent-Based Simulator
par: Gao, Zhijian, et autres
Publié: (2026)

Can Large Language Models Implement Agent-Based Models? An ODD-based Replication Study
par: Fachada, Nuno, et autres
Publié: (2026)

vCause: Efficient and Verifiable Causality Analysis for Cloud-based Endpoint Auditing
par: Song, Qiyang, et autres
Publié: (2026)

High Sensitivity IL-6 ELISA Assay for Accurate Inflammatory Biomarker Detection
par: Xuening, Liu
Publié: (2026)

SafeAgent: Safeguarding LLM Agents via an Automated Risk Simulator
par: Zhou, Xueyang, et autres
Publié: (2025)

Generating Causal Explanations of Vehicular Agent Behavioural Interactions with Learnt Reward Profiles
par: Howard, Rhys, et autres
Publié: (2025)

Agent Guide: A Simple Agent Behavioral Watermarking Framework
par: Huang, Kaibo, et autres
Publié: (2025)

Safe and Policy-Compliant Multi-Agent Orchestration for Enterprise AI
par: Pasupuleti, Vinil, et autres
Publié: (2026)

Investigation of ideal shear strength of dilute binary and ternary Ni-based alloys using first-principles calculations, CALPHAD modeling and correlation analysis
par: Lin, Shuang, et autres
Publié: (2024)

Learning to Seek Evidence: A Verifiable Reasoning Agent with Causal Faithfulness Analysis
par: Huang, Yuhang, et autres
Publié: (2025)

Experiments with Body Agent Architecture
par: Ayuso, Alessandro
Publié: (2022)

Detecting and Mitigating SQL Injection Vulnerabilities in Web Applications
par: Neupane, Sagar
Publié: (2025)

When Prompts Become Payloads: A Framework for Mitigating SQL Injection Attacks in Large Language Model-Driven Applications
par: Motlagh, Farzad Nourmohammadzadeh, et autres
Publié: (2026)

Market-Alignment Risk in Pricing Agents: Trace Diagnostics and Trace-Prior RL under Hidden Competitor State
par: Zhu, Peiying, et autres
Publié: (2026)

Agent Memory Below the Prompt: Persistent Q4 KV Cache for Multi-Agent LLM Inference on Edge Devices
par: Shkolnikov, Yakov Pyotr
Publié: (2026)

Exploring Neural Granger Causality with xLSTMs: Unveiling Temporal Dependencies in Complex Data
par: Poonia, Harsh, et autres
Publié: (2025)

RADEP: A Resilient Adaptive Defense Framework Against Model Extraction Attacks
par: Chakraborty, Amit, et autres
Publié: (2025)

David vs. Goliath: Verifiable Agent-to-Agent Jailbreaking via Reinforcement Learning
par: Nellessen, Samuel, et autres
Publié: (2026)

Cross-LLM Generalization of Behavioral Backdoor Detection in AI Agent Supply Chains
par: Sanna, Arun Chowdary
Publié: (2025)

Understanding the Effectiveness of LLMs in Automated Self-Admitted Technical Debt Repayment
par: Sheikhaei, Mohammad Sadegh, et autres
Publié: (2025)

Operationalizing Cybersecurity Governance for Mitigation Planning with Attack-Path Modeling and Reinforcement Learning
par: Huff, Philip, et autres
Publié: (2026)

Beyond Static Sandboxing: Learned Capability Governance for Autonomous AI Agents
par: Sidik, Bronislav, et autres
Publié: (2026)

Detecting Prompt Injection Attacks Against Application Using Classifiers
par: Shaheer, Safwan, et autres
Publié: (2025)

Beyond the Benchmark: Innovative Defenses Against Prompt Injection Attacks
par: Shaheer, Safwan, et autres
Publié: (2025)

Mindscape: Research of high-information density street environments based on electroencephalogram recording and virtual reality head-mounted simulation
par: Liu, Yijiang, et autres
Publié: (2024)

Quantum-Enhanced Recurrent Neural Networks via Variational Quantum Gating for Battery State of Health Prediction
par: Xu, Yin, et autres
Publié: (2026)

Detecting Sleeper Agents in Large Language Models via Semantic Drift Analysis
par: Zanbaghi, Shahin, et autres
Publié: (2025)

SIGGesture: Generalized Co-Speech Gesture Synthesis via Semantic Injection with Large-Scale Pre-Training Diffusion Models
par: Cheng, Qingrong, et autres
Publié: (2024)

What Makes a Good Terminal-Agent Benchmark Task: A Guideline for Adversarial, Difficult, and Legible Evaluation Design
par: Bercovich, Ivan
Publié: (2026)

DexterCap: An Affordable and Automated System for Capturing Dexterous Hand-Object Manipulation
par: Liang, Yutong, et autres
Publié: (2026)

Physical oceanography during Frederick Russell cruise FR87/6
par: Sherwin, Toby
Publié: (2007)

Demand-Driven Context: A Methodology for Building Enterprise Knowledge Bases Through Agent Failure
par: Navakoti, Raj, et autres
Publié: (2026)

Derivative-Free Optimization via Finite Difference Approximation: An Experimental Study
par: Du-Yi, Wang, et autres
Publié: (2024)

Hydrochemistry measured on water bottle samples during G. O. Sars cruise GS90/6
par: Foyn, Lars
Publié: (2007)

Physical oceanography during ATAIR cruise Atair90/6
par: Lange, Wolfgang
Publié: (2007)