LLMs as Hackers: Autonomous Linux Privilege Escalation Attacks

• URL: http://arxiv.org/abs/2310.11409v6
• Date: Wed, 15 Oct 2025 10:14:34 GMT
• Title: LLMs as Hackers: Autonomous Linux Privilege Escalation Attacks
• Authors: Andreas Happe, Aaron Kaplan, Juergen Cito,
• Abstract summary: We introduce hackingBuddyGPT, a fully automated Language Models (LLMs)-driven prototype for autonomous Linux privilege-escalation attacks.<n>We show that GPT-4-Turbo demonstrates high efficacy, successfully exploiting 33-83% of vulnerabilities, a performance comparable to human pen-testers.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Penetration-testing is crucial for identifying system vulnerabilities, with privilege-escalation being a critical subtask to gain elevated access to protected resources. Language Models (LLMs) presents new avenues for automating these security practices by emulating human behavior. However, a comprehensive understanding of LLMs' efficacy and limitations in performing autonomous Linux privilege-escalation attacks remains under-explored. To address this gap, we introduce hackingBuddyGPT, a fully automated LLM-driven prototype designed for autonomous Linux privilege-escalation. We curated a novel, publicly available Linux privilege-escalation benchmark, enabling controlled and reproducible evaluation. Our empirical analysis assesses the quantitative success rates and qualitative operational behaviors of various LLMs -- GPT-3.5-Turbo, GPT-4-Turbo, and Llama3 -- against baselines of human professional pen-testers and traditional automated tools. We investigate the impact of context management strategies, different context sizes, and various high-level guidance mechanisms on LLM performance. Results show that GPT-4-Turbo demonstrates high efficacy, successfully exploiting 33-83% of vulnerabilities, a performance comparable to human pen-testers (75%). In contrast, local models like Llama3 exhibited limited success (0-33%), and GPT-3.5-Turbo achieved moderate rates (16-50%). We show that both high-level guidance and state-management through LLM-driven reflection significantly boost LLM success rates. Qualitative analysis reveals both LLMs' strengths and weaknesses in generating valid commands and highlights challenges in common-sense reasoning, error handling, and multi-step exploitation, particularly with temporal dependencies. Cost analysis indicates that GPT-4-Turbo can achieve human-comparable performance at competitive costs, especially with optimized context management.

Related papers

• LLM Robustness Leaderboard v1 --Technical report [0.0]
  This report accompanies the robustness LLM leaderboard published by PRISM Eval for the Paris AI Action Summit.<n>We introduce PRISM Eval Behavior Elicitation Tool (BET), an AI system performing automated red-teaming through Dynamic Adversarial Optimization.<n>We propose a fine-grained robustness metric estimating the average number of attempts required to elicit harmful behaviors, revealing that attack difficulty varies by over 300-fold across models despite universal vulnerability.
  arXiv  Detail & Related papers  (2025-08-08T13:15:40Z)
• Large Language Models for In-File Vulnerability Localization Can Be "Lost in the End" [6.6389862916575275]
  New development practice requires researchers to investigate whether commonly used LLMs can effectively analyze large file-sized inputs. This paper is to evaluate the effectiveness of several state-of-the-art chat-based LLMs, including the GPT models, in detecting in-file vulnerabilities.
  arXiv  Detail & Related papers  (2025-02-09T14:51:15Z)
• Can LLMs Hack Enterprise Networks? Autonomous Assumed Breach Penetration-Testing Active Directory Networks [1.3124479769761592]
  We introduce a novel prototype designed to employ Large Language Model (LLM)-driven autonomous systems.<n>Our system represents the first demonstration of a fully autonomous, LLM-driven framework capable of compromising accounts.<n>We find that the associated costs are competitive with, and often significantly lower than, those incurred by professional human pen-testers.
  arXiv  Detail & Related papers  (2025-02-06T17:12:43Z)
• Adversarial Reasoning at Jailbreaking Time [49.70772424278124]
  Large language models (LLMs) are becoming more capable and widespread.<n>Recent advances in standardizing, measuring, and scaling test-time compute suggest new methodologies for optimizing models to achieve high performance on hard tasks.<n>In this paper, we apply these advances to the task of model jailbreaking: eliciting harmful responses from aligned LLMs.
  arXiv  Detail & Related papers  (2025-02-03T18:59:01Z)
• The Dual-use Dilemma in LLMs: Do Empowering Ethical Capacities Make a Degraded Utility? [54.18519360412294]
  Large Language Models (LLMs) must balance between rejecting harmful requests for safety and accommodating legitimate ones for utility.<n>This paper presents a Direct Preference Optimization (DPO) based alignment framework that achieves better overall performance.<n>We analyze experimental results obtained from testing DeepSeek-R1 on our benchmark and reveal the critical ethical concerns raised by this highly acclaimed model.
  arXiv  Detail & Related papers  (2025-01-20T06:35:01Z)
• LLM4CVE: Enabling Iterative Automated Vulnerability Repair with Large Language Models [9.946058168276744]
  Large Language Models (LLM) have opened up the possibility for many software defects to be patched automatically. We propose an iterative pipeline that robustly fixes vulnerable functions in real-world code with high accuracy. We achieve a human-verified quality score of 8.51/10 and an increase in groundtruth code similarity of 20% with Llama 3 70B.
  arXiv  Detail & Related papers  (2025-01-07T00:21:42Z)
• AutoPT: How Far Are We from the End2End Automated Web Penetration Testing? [54.65079443902714]
  We introduce AutoPT, an automated penetration testing agent based on the principle of PSM driven by LLMs. Our results show that AutoPT outperforms the baseline framework ReAct on the GPT-4o mini model.
  arXiv  Detail & Related papers  (2024-11-02T13:24:30Z)
• Iterative Self-Tuning LLMs for Enhanced Jailbreaking Capabilities [63.603861880022954]
  We introduce ADV-LLM, an iterative self-tuning process that crafts adversarial LLMs with enhanced jailbreak ability. Our framework significantly reduces the computational cost of generating adversarial suffixes while achieving nearly 100% ASR on various open-source LLMs. It exhibits strong attack transferability to closed-source models, achieving 99% ASR on GPT-3.5 and 49% ASR on GPT-4, despite being optimized solely on Llama3.
  arXiv  Detail & Related papers  (2024-10-24T06:36:12Z)
• Towards Automated Penetration Testing: Introducing LLM Benchmark, Analysis, and Improvements [1.4433703131122861]
  Large language models (LLMs) have shown potential across various domains, including cybersecurity. There is currently no comprehensive, open, end-to-end automated penetration testing benchmark. This paper introduces a novel open benchmark for LLM-based automated penetration testing.
  arXiv  Detail & Related papers  (2024-10-22T16:18:41Z)
• Comparison of Static Application Security Testing Tools and Large Language Models for Repo-level Vulnerability Detection [11.13802281700894]
  Static Application Security Testing (SAST) is usually utilized to scan source code for security vulnerabilities. Deep learning (DL)-based methods have demonstrated their potential in software vulnerability detection. This paper compares 15 diverse SAST tools with 12 popular or state-of-the-art open-source LLMs in detecting software vulnerabilities.
  arXiv  Detail & Related papers  (2024-07-23T07:21:14Z)
• Automated Progressive Red Teaming [38.723546092060666]
  Manual red teaming is time-consuming, costly and lacks scalability. We propose Automated Progressive Red Teaming (APRT) as an effectively learnable framework. APRT leverages three core modules: an Intention Expanding LLM that generates diverse initial attack samples, an Intention Hiding LLM that crafts adversarial prompts, and an Evil Maker to manage prompt diversity and filter ineffective samples.
  arXiv  Detail & Related papers  (2024-07-04T12:14:27Z)
• AutoDetect: Towards a Unified Framework for Automated Weakness Detection in Large Language Models [95.09157454599605]
  Large Language Models (LLMs) are becoming increasingly powerful, but they still exhibit significant but subtle weaknesses. Traditional benchmarking approaches cannot thoroughly pinpoint specific model deficiencies. We introduce a unified framework, AutoDetect, to automatically expose weaknesses in LLMs across various tasks.
  arXiv  Detail & Related papers  (2024-06-24T15:16:45Z)
• SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal Behaviors [64.9938658716425]
  Existing evaluations of large language models' (LLMs) ability to recognize and reject unsafe user requests face three limitations. First, existing methods often use coarse-grained of unsafe topics, and are over-representing some fine-grained topics. Second, linguistic characteristics and formatting of prompts are often overlooked, like different languages, dialects, and more -- which are only implicitly considered in many evaluations. Third, existing evaluations rely on large LLMs for evaluation, which can be expensive.
  arXiv  Detail & Related papers  (2024-06-20T17:56:07Z)
• LLM Agents can Autonomously Exploit One-day Vulnerabilities [2.3999111269325266]
  We show that LLM agents can autonomously exploit one-day vulnerabilities in real-world systems. Our GPT-4 agent requires the CVE description for high performance. Our findings raise questions around the widespread deployment of highly capable LLM agents.
  arXiv  Detail & Related papers  (2024-04-11T22:07:19Z)
• LLM4Vuln: A Unified Evaluation Framework for Decoupling and Enhancing LLMs' Vulnerability Reasoning [20.463200377413255]
  We introduce a unified evaluation framework that separates and assesses vulnerability reasoning capabilities. We conduct experiments using 147 ground-truth vulnerabilities and 147 non-vulnerable cases in Solidity, Java and C/C++, testing them in a total of 3,528 scenarios. Our findings reveal the varying impacts of knowledge enhancement, context supplementation, and prompt schemes.
  arXiv  Detail & Related papers  (2024-01-29T14:32:27Z)
• Large Language Models as Automated Aligners for benchmarking Vision-Language Models [48.4367174400306]
  Vision-Language Models (VLMs) have reached a new level of sophistication, showing notable competence in executing intricate cognition and reasoning tasks. Existing evaluation benchmarks, primarily relying on rigid, hand-crafted datasets, face significant limitations in assessing the alignment of these increasingly anthropomorphic models with human intelligence. In this work, we address the limitations via Auto-Bench, which delves into exploring LLMs as proficient curation, measuring the alignment betweenVLMs and human intelligence and value through automatic data curation and assessment.
  arXiv  Detail & Related papers  (2023-11-24T16:12:05Z)
• SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks [99.23352758320945]
  We propose SmoothLLM, the first algorithm designed to mitigate jailbreaking attacks on large language models (LLMs) Based on our finding that adversarially-generated prompts are brittle to character-level changes, our defense first randomly perturbs multiple copies of a given input prompt, and then aggregates the corresponding predictions to detect adversarial inputs.
  arXiv  Detail & Related papers  (2023-10-05T17:01:53Z)
• Can Large Language Models Find And Fix Vulnerable Software? [0.0]
  GPT-4 identified approximately four times the vulnerabilities than its counterparts. It provided viable fixes for each vulnerability, demonstrating a low rate of false positives. GPT-4's code corrections led to a 90% reduction in vulnerabilities, requiring only an 11% increase in code lines.
  arXiv  Detail & Related papers  (2023-08-20T19:33:12Z)
• Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection [64.67495502772866]
  Large Language Models (LLMs) are increasingly being integrated into various applications. We show how attackers can override original instructions and employed controls using Prompt Injection attacks. We derive a comprehensive taxonomy from a computer security perspective to systematically investigate impacts and vulnerabilities.
  arXiv  Detail & Related papers  (2023-02-23T17:14:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.