Imagen de Portada

How Reliable Are AI Attackers Against a Fixed Vulnerable Target? A 400-Run Empirical Study of LLM Penetration Testing Consistency

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autor principal:	Erdem, Galip Tolga
Formato:	Preprint
Publicado:	2026
Materias:	Cryptography and Security Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Next-Generation Phishing: How LLM Agents Empower Cyber Attackers
por: Afane, Khalifa, et al.
Publicado: (2024)

Multi-Agent Penetration Testing AI for the Web
por: David, Isaac, et al.
Publicado: (2025)

Towards Automated Penetration Testing: Introducing LLM Benchmark, Analysis, and Improvements
por: Isozaki, Isamu, et al.
Publicado: (2024)

RapidPen: Fully Automated IP-to-Shell Penetration Testing with LLM-based Agents
por: Nakatani, Sho
Publicado: (2025)

Penetration Testing of Agentic AI: A Comparative Security Analysis Across Models and Frameworks
por: Nguyen, Viet K., et al.
Publicado: (2025)

How Effective Are Neural Networks for Fixing Security Vulnerabilities
por: Wu, Yi, et al.
Publicado: (2023)

Reinforcement Learning for Automated Cybersecurity Penetration Testing
por: López-Montero, Daniel, et al.
Publicado: (2025)

AutoPT: How Far Are We from the End2End Automated Web Penetration Testing?
por: Wu, Benlong, et al.
Publicado: (2024)

Vulnerabilities in AI Code Generators: Exploring Targeted Data Poisoning Attacks
por: Cotroneo, Domenico, et al.
Publicado: (2023)

AWE: Adaptive Agents for Dynamic Web Penetration Testing
por: Jaswal, Akshat Singh, et al.
Publicado: (2026)

PentestMCP: A Toolkit for Agentic Penetration Testing
por: Ezetta, Zachary, et al.
Publicado: (2025)

Tailored Prompts, Targeted Protection: Vulnerability-Specific LLM Analysis for Smart Contracts
por: Zhang, Xing, et al.
Publicado: (2026)

Phantom Transfer: Data-level Defences are Insufficient Against Data Poisoning
por: Draganov, Andrew, et al.
Publicado: (2026)

Taught by the Flawed: How Dataset Insecurity Breeds Vulnerable AI Code
por: Xia, Catherine, et al.
Publicado: (2025)

Lessons from Penetration Tests on Large-Scale Agent Systems
por: Eykholt, Kevin, et al.
Publicado: (2026)

AutoPenBench: Benchmarking Generative Agents for Penetration Testing
por: Gioacchini, Luca, et al.
Publicado: (2024)

Generative AI in Cybersecurity: A Comprehensive Review of LLM Applications and Vulnerabilities
por: Ferrag, Mohamed Amine, et al.
Publicado: (2024)

An Empirical Study of Vulnerabilities in Python Packages and Their Detection
por: Quan, Haowei, et al.
Publicado: (2025)

APT-Agent: Automated Penetration Testing using Large Language Models
por: Li, William Guanting, et al.
Publicado: (2026)

Comparing AI Agents to Cybersecurity Professionals in Real-World Penetration Testing
por: Lin, Justin W., et al.
Publicado: (2025)

Leveraging AI to optimize website structure discovery during Penetration Testing
por: Antonelli, Diego, et al.
Publicado: (2021)

Hackers or Hallucinators? A Comprehensive Analysis of LLM-Based Automated Penetration Testing
por: Peng, Jiaren, et al.
Publicado: (2026)

Pen-Strategist: A Reasoning Framework for Penetration Testing Strategy Formation and Analysis
por: Ginige, Yasod, et al.
Publicado: (2026)

No Attacker Needed: Unintentional Cross-User Contamination in Shared-State LLM Agents
por: Yang, Tiankai, et al.
Publicado: (2026)

What Breaks Embodied AI Security:LLM Vulnerabilities, CPS Flaws,or Something Else?
por: Ma, Boyang, et al.
Publicado: (2026)

An Empirical Study of Vulnerability Detection using Federated Learning
por: Zhou, Peiheng, et al.
Publicado: (2024)

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

The System Prompt Is the Attack Surface: How LLM Agent Configuration Shapes Security and Creates Exploitable Vulnerabilities
por: Litvak, Ron
Publicado: (2026)

How Vulnerable Are AI Agents to Indirect Prompt Injections? Insights from a Large-Scale Public Competition
por: Dziemian, Mateusz, et al.
Publicado: (2026)

Hacking Back the AI-Hacker: Prompt Injection as a Defense Against LLM-driven Cyberattacks
por: Pasquini, Dario, et al.
Publicado: (2024)

Bridging AI and Software Security: A Comparative Vulnerability Assessment of LLM Agent Deployment Paradigms
por: Gasmi, Tarek, et al.
Publicado: (2025)

Uplifted Attackers, Human Defenders: The Cyber Offense-Defense Balance for Trailing-Edge Organizations
por: Murphy, Benjamin, et al.
Publicado: (2025)

DeSIA: Attribute Inference Attacks Against Limited Fixed Aggregate Statistics
por: Mao, Yifeng, et al.
Publicado: (2025)

Running in CIRCLE? A Simple Benchmark for LLM Code Interpreter Security
por: Chua, Gabriel
Publicado: (2025)

How Far Are VLMs from Privacy Awareness in the Physical World? An Empirical Study
por: Wang, Junran, et al.
Publicado: (2026)

AutoAttacker: A Large Language Model Guided System to Implement Automatic Cyber-attacks
por: Xu, Jiacen, et al.
Publicado: (2024)

SecureFixAgent: A Hybrid LLM Agent for Automated Python Static Vulnerability Repair
por: Gajjar, Jugal, et al.
Publicado: (2025)

LProtector: An LLM-driven Vulnerability Detection System
por: Sheng, Ze, et al.
Publicado: (2024)

Life-Cycle Routing Vulnerabilities of LLM Router
por: Lin, Qiqi, et al.
Publicado: (2025)

Credential Leakage in LLM Agent Skills: A Large-Scale Empirical Study
por: Chen, Zhihao, et al.
Publicado: (2026)