LLM4Vuln: A Unified Evaluation Framework for Decoupling and Enhancing LLMs' Vulnerability Reasoning

• URL: http://arxiv.org/abs/2401.16185v3
• Date: Mon, 13 Jan 2025 06:10:24 GMT
• Title: LLM4Vuln: A Unified Evaluation Framework for Decoupling and Enhancing LLMs' Vulnerability Reasoning
• Authors: Yuqiang Sun, Daoyuan Wu, Yue Xue, Han Liu, Wei Ma, Lyuye Zhang, Yang Liu, Yingjiu Li,
• Abstract summary: 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.
• Score: 20.463200377413255
• License:
• Abstract: Large language models (LLMs) have demonstrated significant potential in various tasks, including those requiring human-level intelligence, such as vulnerability detection. However, recent efforts to use LLMs for vulnerability detection remain preliminary, as they lack a deep understanding of whether a subject LLM's vulnerability reasoning capability stems from the model itself or from external aids such as knowledge retrieval and tooling support. In this paper, we aim to decouple LLMs' vulnerability reasoning from other capabilities, such as vulnerability knowledge adoption, context information retrieval, and advanced prompt schemes. We introduce LLM4Vuln, a unified evaluation framework that separates and assesses LLMs' vulnerability reasoning capabilities and examines improvements when combined with other enhancements. We conduct controlled 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 across four LLMs (GPT-3.5, GPT-4, Phi-3, and Llama 3). Our findings reveal the varying impacts of knowledge enhancement, context supplementation, and prompt schemes. We also identify 14 zero-day vulnerabilities in four pilot bug bounty programs, resulting in $3,576 in bounties.

Related papers

• Do LLMs Consider Security? An Empirical Study on Responses to Programming Questions [10.69738882390809]
  ChatGPT can volunteer context-specific information to developers, promoting safe coding practices. We evaluate the degree of security awareness exhibited by three prominent LLMs: Claude 3, GPT-4, and Llama 3. Our findings show that all three models struggle to accurately detect and warn users about vulnerabilities, achieving a detection rate of only 12.6% to 40% across our datasets.
  arXiv  Detail & Related papers  (2025-02-20T02:20:06Z)
• Code Change Intention, Development Artifact and History Vulnerability: Putting Them Together for Vulnerability Fix Detection by LLM [13.278153690972243]
  VulFixMiner and CoLeFunDa focus solely on code changes, neglecting essential context from development artifacts. We propose LLM4VFD, a novel framework that leverages Large Language Models (LLMs) enhanced with Chain-of-Thought reasoning and In-Context Learning.
  arXiv  Detail & Related papers  (2025-01-24T23:40:03Z)
• GIVE: Structured Reasoning of Large Language Models with Knowledge Graph Inspired Veracity Extrapolation [108.2008975785364]
  Graph Inspired Veracity Extrapolation (GIVE) is a novel reasoning method that merges parametric and non-parametric memories to improve accurate reasoning with minimal external input. GIVE guides the LLM agent to select the most pertinent expert data (observe), engage in query-specific divergent thinking (reflect), and then synthesize this information to produce the final output (speak)
  arXiv  Detail & Related papers  (2024-10-11T03:05:06Z)
• Exploring Automatic Cryptographic API Misuse Detection in the Era of LLMs [60.32717556756674]
  This paper introduces a systematic evaluation framework to assess Large Language Models in detecting cryptographic misuses. Our in-depth analysis of 11,940 LLM-generated reports highlights that the inherent instabilities in LLMs can lead to over half of the reports being false positives. The optimized approach achieves a remarkable detection rate of nearly 90%, surpassing traditional methods and uncovering previously unknown misuses in established benchmarks.
  arXiv  Detail & Related papers  (2024-07-23T15:31:26Z)
• 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)
• FAC$^2$E: Better Understanding Large Language Model Capabilities by Dissociating Language and Cognition [56.76951887823882]
  Large language models (LLMs) are primarily evaluated by overall performance on various text understanding and generation tasks. We present FAC$2$E, a framework for Fine-grAined and Cognition-grounded LLMs' Capability Evaluation.
  arXiv  Detail & Related papers  (2024-02-29T21:05:37Z)
• Benchmarking and Defending Against Indirect Prompt Injection Attacks on Large Language Models [79.0183835295533]
  We introduce the first benchmark for indirect prompt injection attacks, named BIPIA, to assess the risk of such vulnerabilities. Our analysis identifies two key factors contributing to their success: LLMs' inability to distinguish between informational context and actionable instructions, and their lack of awareness in avoiding the execution of instructions within external content. We propose two novel defense mechanisms-boundary awareness and explicit reminder-to address these vulnerabilities in both black-box and white-box settings.
  arXiv  Detail & Related papers  (2023-12-21T01:08:39Z)
• How Far Have We Gone in Vulnerability Detection Using Large Language Models [15.09461331135668]
  We introduce a comprehensive vulnerability benchmark VulBench. This benchmark aggregates high-quality data from a wide range of CTF challenges and real-world applications. We find that several LLMs outperform traditional deep learning approaches in vulnerability detection.
  arXiv  Detail & Related papers  (2023-11-21T08:20:39Z)
• LLMs as Hackers: Autonomous Linux Privilege Escalation Attacks [0.0]
  We explore the intersection of Language Models (LLMs) and penetration testing. We introduce a fully automated privilege-escalation tool for evaluating the efficacy of LLMs for (ethical) hacking. We analyze the impact of different context sizes, in-context learning, optional high-level mechanisms, and memory management techniques.
  arXiv  Detail & Related papers  (2023-10-17T17:15:41Z)
• 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)

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.