Copertina

ARGUS: Defending LLM Agents Against Context-Aware Prompt Injection

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Weng, Shihao, Feng, Yang, Zhang, Jinrui, Xie, Xiaofei, Yu, Jiongchi, Liu, Jia
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Cryptography and Security Software Engineering
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Chimera: Harnessing Multi-Agent LLMs for Automatic Insider Threat Simulation
di: Yu, Jiongchi, et al.
Pubblicazione: (2025)

Understanding the Supply Chain and Risks of Large Language Model Applications
di: Ma, Yujie, et al.
Pubblicazione: (2025)

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

CAShift: Benchmarking Log-Based Cloud Attack Detection under Normality Shift
di: Yu, Jiongchi, et al.
Pubblicazione: (2025)

What Makes a Good LLM Agent for Real-world Penetration Testing?
di: Deng, Gelei, et al.
Pubblicazione: (2026)

Model Context Protocol Threat Modeling and Analyzing Vulnerabilities to Prompt Injection with Tool Poisoning
di: Huang, Charoes, et al.
Pubblicazione: (2026)

Investigating Detection and Obfuscation of Prompt Injection Attacks Against Software Reverse Engineering AI Agents
di: Crawford, Brian, et al.
Pubblicazione: (2026)

Prompt Injection attack against LLM-integrated Applications
di: Liu, Yi, et al.
Pubblicazione: (2023)

Are AI-assisted Development Tools Immune to Prompt Injection?
di: Huang, Charoes, et al.
Pubblicazione: (2026)

"Your AI, My Shell": Demystifying Prompt Injection Attacks on Agentic AI Coding Editors
di: Liu, Yue, et al.
Pubblicazione: (2025)

Towards Demystifying and Repairing LLM-in-the-Loop Vulnerabilities
di: Ma, Yujie, et al.
Pubblicazione: (2026)

Towards Understanding and Characterizing Vulnerabilities in Intelligent Connected Vehicles through Real-World Exploits
di: Wang, Yuelin, et al.
Pubblicazione: (2026)

Defending Code Language Models against Backdoor Attacks with Deceptive Cross-Entropy Loss
di: Yang, Guang, et al.
Pubblicazione: (2024)

Exposing and Defending Membership Leakage in Vulnerability Prediction Models
di: Liao, Yihan, et al.
Pubblicazione: (2025)

FCGHunter: Towards Evaluating Robustness of Graph-Based Android Malware Detection
di: Song, Shiwen, et al.
Pubblicazione: (2025)

ACFIX: Guiding LLMs with Mined Common RBAC Practices for Context-Aware Repair of Access Control Vulnerabilities in Smart Contracts
di: Zhang, Lyuye, et al.
Pubblicazione: (2024)

zkCraft: Prompt-Guided LLM as a Zero-Shot Mutation Pattern Oracle for TCCT-Powered ZK Fuzzing
di: Fu, Rong, et al.
Pubblicazione: (2026)

SCAFFOLD-CEGIS: Preventing Latent Security Degradation in LLM-Driven Iterative Code Refinement
di: Chen, Yi, et al.
Pubblicazione: (2026)

PatchFuzz: Patch Fuzzing for JavaScript Engines
di: Wang, Junjie, et al.
Pubblicazione: (2025)

Identifying Adversary Tactics and Techniques in Malware Binaries with an LLM Agent
di: Xuan, Zhou, et al.
Pubblicazione: (2026)

From LLMs to Agents: A Comparative Evaluation of LLMs and LLM-based Agents in Security Patch Detection
di: Han, Junxiao, et al.
Pubblicazione: (2025)

VULPO: Context-Aware Vulnerability Detection via On-Policy LLM Optimization
di: Li, Youpeng, et al.
Pubblicazione: (2025)

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

PentestEval: Benchmarking LLM-based Penetration Testing with Modular and Stage-Level Design
di: Yang, Ruozhao, et al.
Pubblicazione: (2025)

Beyond Function-Level Analysis: Context-Aware Reasoning for Inter-Procedural Vulnerability Detection
di: Li, Yikun, et al.
Pubblicazione: (2026)

HarnessAgent: Scaling Automatic Fuzzing Harness Construction with Tool-Augmented LLM Pipelines
di: Yang, Kang, et al.
Pubblicazione: (2025)

LLM Agents for Automated Web Vulnerability Reproduction: Are We There Yet?
di: Liu, Bin, et al.
Pubblicazione: (2025)

Prompt Fuzzing for Fuzz Driver Generation
di: Lyu, Yunlong, et al.
Pubblicazione: (2023)

Exploiting LLM Agent Supply Chains via Payload-less Skills
di: Liu, Xinyu, et al.
Pubblicazione: (2026)

DLAP: A Deep Learning Augmented Large Language Model Prompting Framework for Software Vulnerability Detection
di: Yang, Yanjing, et al.
Pubblicazione: (2024)

Who Tests the Testers? Systematic Enumeration and Coverage Audit of LLM Agent Tool Call Safety
di: Chen, Xuan, et al.
Pubblicazione: (2026)

SABER: Benchmarking Operational Safety of LLM Coding Agents in Stateful Project Workspaces
di: Hu, Qi, et al.
Pubblicazione: (2026)

GraphQLer: Enhancing GraphQL Security with Context-Aware API Testing
di: Tsai, Omar, et al.
Pubblicazione: (2025)

How Secure is Secure Code Generation? Adversarial Prompts Put LLM Defenses to the Test
di: Tessa, Melissa, et al.
Pubblicazione: (2026)

Enhancing REST API Fuzzing with Access Policy Violation Checks and Injection Attacks
di: Sahin, Omur, et al.
Pubblicazione: (2026)

Demonstration Attack against In-Context Learning for Code Intelligence
di: Ge, Yifei, et al.
Pubblicazione: (2024)

TPSQLi: Test Prioritization for SQL Injection Vulnerability Detection in Web Applications
di: Yang, Guan-Yan, et al.
Pubblicazione: (2025)

Pinning Is Futile: You Need More Than Local Dependency Versioning to Defend against Supply Chain Attacks
di: He, Hao, et al.
Pubblicazione: (2025)

Probing Privacy Leaks in LLM-based Code Generation via Test Generation
di: Ge, Yifei, et al.
Pubblicazione: (2026)

KEENHash: Hashing Programs into Function-Aware Embeddings for Large-Scale Binary Code Similarity Analysis
di: Liu, Zhijie, et al.
Pubblicazione: (2025)