LLM Agent Honeypot: Monitoring AI Hacking Agents in the Wild

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Reworr, Volkov, Dmitrii
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866913685725773824
author Reworr
Volkov, Dmitrii
author_facet Reworr
Volkov, Dmitrii
contents Attacks powered by Large Language Model (LLM) agents represent a growing threat to modern cybersecurity. To address this concern, we present LLM Honeypot, a system designed to monitor autonomous AI hacking agents. By augmenting a standard SSH honeypot with prompt injection and time-based analysis techniques, our framework aims to distinguish LLM agents among all attackers. Over a trial deployment of about three months in a public environment, we collected 8,130,731 hacking attempts and 8 potential AI agents. Our work demonstrates the emergence of AI-driven threats and their current level of usage, serving as an early warning of malicious LLM agents in the wild.
format Preprint
id arxiv_https___arxiv_org_abs_2410_13919
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle LLM Agent Honeypot: Monitoring AI Hacking Agents in the Wild
Reworr
Volkov, Dmitrii
Cryptography and Security
Artificial Intelligence
Attacks powered by Large Language Model (LLM) agents represent a growing threat to modern cybersecurity. To address this concern, we present LLM Honeypot, a system designed to monitor autonomous AI hacking agents. By augmenting a standard SSH honeypot with prompt injection and time-based analysis techniques, our framework aims to distinguish LLM agents among all attackers. Over a trial deployment of about three months in a public environment, we collected 8,130,731 hacking attempts and 8 potential AI agents. Our work demonstrates the emergence of AI-driven threats and their current level of usage, serving as an early warning of malicious LLM agents in the wild.
title LLM Agent Honeypot: Monitoring AI Hacking Agents in the Wild
topic Cryptography and Security
Artificial Intelligence
url https://arxiv.org/abs/2410.13919