Towards Demystifying and Repairing LLM-in-the-Loop Vulnerabilities

• URL: http://arxiv.org/abs/2605.28893v1
• Date: Wed, 27 May 2026 08:11:37 GMT
• Title: Towards Demystifying and Repairing LLM-in-the-Loop Vulnerabilities
• Abstract summary: Large Language Models (LLMs) have been actively integrated into modern software systems as critical components.<n>LLMs-in-the-loop vulnerabilities, where vulnerabilities are introduced by LLMs and their dependent downstream components, such as frameworks, introduce new risks.<n>These vulnerabilities are more challenging to precisely fix, especially for those involving prompt injections where the Pass@1 rate is only 28.57%.
• Score: 22.313168715963315
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large Language Models(LLMs) have been actively integrated into modern software systems as critical components. LLM-in-the-loop vulnerabilities, where vulnerabilities are introduced by LLMs and their dependent downstream components, such as frameworks, introduce new risks. Although some benchmark datasets have been constructed to study the impact of such vulnerabilities, most works still remain at the analysis from the conventional software level, ignoring the harm actually caused by LLMs. Understanding real-world LLM-in-the-loop vulnerabilities is still an open problem. To address this gap, we build the first LLM-in-the-loop vulnerability dataset, LLMCVE, to facilitate the risk analysis of LLM-integrated software. To do so, we first collect 2,888 multi-source vulnerabilities across 230 popular LLM components. Then, through manual analysis, we identify 205 vulnerabilities that strictly fall under the concept of LLM-in-the-loop vulnerability. Through analysis, we found that LLMs more often play as targets or propagation vectors rather than the root cause of these vulnerabilities. Furthermore, based on LLMCVE, we evaluate the repairing capabilities of existing agent-based vulnerability repair methods, such as SWE-Agent. Experimental results demonstrate that compared to conventional software vulnerabilities, LLM-in-the-Loop vulnerabilities are more challenging to precisely fix, especially for those involving prompt injections where the Pass@1 rate is only 28.57%.

Related papers

• Large Language Models in Misinformation Ecosystems: Misuse, Defense, and Vulnerability [65.56750741053266]
  Large language models (LLMs) have transformed misinformation from a content-centric problem into a broader ecosystem-level security challenge.<n>In this paper, we introduce a role-layer framework to unify these risks and defenses.<n>The role characterizes LLMs as attackers, defenders, and vulnerable components of verification systems, while the layer dimension covers content, social contexts, evidence environments, and verification.
  arXiv  Detail & Related papers  (2026-07-11T17:04:17Z)
• On the Effectiveness of Instruction-Tuning Local LLMs for Identifying Software Vulnerabilities [0.7136933021609079]
  Large Language Models (LLMs) show significant promise in automating software vulnerability analysis.<n>Current approaches in using LLMs to automate vulnerability analysis mostly rely on using online API-based LLM services.<n>This paper addresses these limitations by reformulating the problem as Software Vulnerability Identification (SVI)<n>We show that instruct-tuned local models represent a more effective, secure, and practical approach for leveraging LLMs in real-world vulnerability management.
  arXiv  Detail & Related papers  (2025-12-23T05:30:53Z)
• Evaluating LLMs for One-Shot Patching of Real and Artificial Vulnerabilities [2.5190317156807924]
  We empirically evaluate the patching effectiveness and complementarity of several prominent Large Language Models (LLMs)<n>Our results reveal that LLMs patch real vulnerabilities more effectively compared to artificial ones.<n>Our analysis reveals significant variability across LLMs in terms of overlapping (multiple LLMs patching the same vulnerabilities) and complementarity.
  arXiv  Detail & Related papers  (2025-11-28T18:03:47Z)
• Commercial LLM Agents Are Already Vulnerable to Simple Yet Dangerous Attacks [88.84977282952602]
  A high volume of recent ML security literature focuses on attacks against aligned large language models (LLMs)<n>In this paper, we analyze security and privacy vulnerabilities that are unique to LLM agents.<n>We conduct a series of illustrative attacks on popular open-source and commercial agents, demonstrating the immediate practical implications of their vulnerabilities.
  arXiv  Detail & Related papers  (2025-02-12T17:19:36Z)
• 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)
• From Vulnerabilities to Remediation: A Systematic Literature Review of LLMs in Code Security [0.0]
  Large Language Models (LLMs) have emerged as powerful tools for automating various programming tasks.<n>LLMs could introduce vulnerabilities unbeknown to the programmer.<n>When analyzing code, they could miss clear vulnerabilities or signal nonexistent ones.
  arXiv  Detail & Related papers  (2024-12-19T16:20:22Z)
• Look Before You Leap: Enhancing Attention and Vigilance Regarding Harmful Content with GuidelineLLM [53.79753074854936]
  Large language models (LLMs) are increasingly vulnerable to emerging jailbreak attacks.<n>This vulnerability poses significant risks to real-world applications.<n>We propose a novel defensive paradigm called GuidelineLLM.
  arXiv  Detail & Related papers  (2024-12-10T12:42:33Z)
• 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)
• Harnessing Large Language Models for Software Vulnerability Detection: A Comprehensive Benchmarking Study [1.03590082373586]
  We propose using large language models (LLMs) to assist in finding vulnerabilities in source code. The aim is to test multiple state-of-the-art LLMs and identify the best prompting strategies. We find that LLMs can pinpoint many more issues than traditional static analysis tools, outperforming traditional tools in terms of recall and F1 scores.
  arXiv  Detail & Related papers  (2024-05-24T14:59:19Z)
• Uncovering Safety Risks of Large Language Models through Concept Activation Vector [13.804245297233454]
  We introduce a Safety Concept Activation Vector (SCAV) framework to guide attacks on large language models (LLMs)<n>We then develop an SCAV-guided attack method that can generate both attack prompts and embedding-level attacks.<n>Our attack method significantly improves the attack success rate and response quality while requiring less training data.
  arXiv  Detail & Related papers  (2024-04-18T09:46:25Z)
• Multitask-based Evaluation of Open-Source LLM on Software Vulnerability [2.7692028382314815]
  This paper proposes a pipeline for quantitatively evaluating interactive Large Language Models (LLMs) using publicly available datasets. We carry out an extensive technical evaluation of LLMs using Big-Vul covering four different common software vulnerability tasks. We find that the existing state-of-the-art approaches and pre-trained Language Models (LMs) are generally superior to LLMs in software vulnerability detection.
  arXiv  Detail & Related papers  (2024-04-02T15:52:05Z)
• 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.<n>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.<n>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)
• Understanding the Effectiveness of Large Language Models in Detecting Security Vulnerabilities [12.82645410161464]
  We evaluate the effectiveness of 16 pre-trained Large Language Models on 5,000 code samples from five diverse security datasets. Overall, LLMs show modest effectiveness in detecting vulnerabilities, obtaining an average accuracy of 62.8% and F1 score of 0.71 across datasets. We find that advanced prompting strategies that involve step-by-step analysis significantly improve performance of LLMs on real-world datasets in terms of F1 score (by upto 0.18 on average)
  arXiv  Detail & Related papers  (2023-11-16T13:17:20Z)

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.