Hacking CTFs with Plain Agents

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Turtayev, Rustem, Petrov, Artem, Volkov, Dmitrii, Volk, Denis
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912143224340480
author Turtayev, Rustem
Petrov, Artem
Volkov, Dmitrii
Volk, Denis
author_facet Turtayev, Rustem
Petrov, Artem
Volkov, Dmitrii
Volk, Denis
contents We saturate a high-school-level hacking benchmark with plain LLM agent design. Concretely, we obtain 95% performance on InterCode-CTF, a popular offensive security benchmark, using prompting, tool use, and multiple attempts. This beats prior work by Phuong et al. 2024 (29%) and Abramovich et al. 2024 (72%). Our results suggest that current LLMs have surpassed the high school level in offensive cybersecurity. Their hacking capabilities remain underelicited: our ReAct&Plan prompting strategy solves many challenges in 1-2 turns without complex engineering or advanced harnessing.
format Preprint
id arxiv_https___arxiv_org_abs_2412_02776
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Hacking CTFs with Plain Agents
Turtayev, Rustem
Petrov, Artem
Volkov, Dmitrii
Volk, Denis
Cryptography and Security
Artificial Intelligence
We saturate a high-school-level hacking benchmark with plain LLM agent design. Concretely, we obtain 95% performance on InterCode-CTF, a popular offensive security benchmark, using prompting, tool use, and multiple attempts. This beats prior work by Phuong et al. 2024 (29%) and Abramovich et al. 2024 (72%). Our results suggest that current LLMs have surpassed the high school level in offensive cybersecurity. Their hacking capabilities remain underelicited: our ReAct&Plan prompting strategy solves many challenges in 1-2 turns without complex engineering or advanced harnessing.
title Hacking CTFs with Plain Agents
topic Cryptography and Security
Artificial Intelligence
url https://arxiv.org/abs/2412.02776