MAS-SZZ: Multi-Agentic SZZ Algorithm for Vulnerability-Inducing Commit Identification

• URL: http://arxiv.org/abs/2604.24398v1
• Date: Mon, 27 Apr 2026 12:23:48 GMT
• Title: MAS-SZZ: Multi-Agentic SZZ Algorithm for Vulnerability-Inducing Commit Identification
• Abstract summary: A straightforward solution is the SZZ algorithm, which traces back through the code history to identify the earliest commit that modify the vulnerable code.<n>We propose a multi-agentic SZZ algorithm, named MAS-SZZ, that facilitates the identification of vulnerability-inducing commits through collaboration among agents.
• Score: 15.525995216533424
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Accurate vulnerability-inducing commit identification serves as a foundation for a series of software security tasks, such as vulnerability detection and affected version analysis. A straightforward solution is the SZZ algorithm, which traces back through the code history to identify the earliest commit that modify the vulnerable code. Unfortunately, neither the customized V-SZZ nor state-of-the-art LLM4SZZ perform satisfactorily due to the incorrect anchor selection and inadequate backtracking capability, making them far beyond a reliable usage in practice. To overcome these challenges, we propose a multi-agentic SZZ algorithm, named MAS-SZZ, that facilitates the identification of vulnerability-inducing commits through collaboration among agents. Specifically, given a CVE description and its corresponding fixing commit, MAS-SZZ summarizes the root cause of the vulnerability and employs a structured step-forward prompting strategy to localize vulnerability-related statements based on the change intent of each patch hunk. These vulnerable statements serve as anchors from which MAS-SZZ autonomously traces backward through the repository's history to find the commit that first introduced the vulnerability. Extensive experiments show that MAS-SZZ outperforms the state-of-the-art baselines across datasets and programming languages, achieving F1-score gains of up to 65.22% over the best-performing SZZ algorithm.

Related papers

• Reasoning-Aware AIGC Detection via Alignment and Reinforcement [55.09684020007737]
  REVEAL is a framework that generates interpretable reasoning chains before classification.<n>It achieves state-of-the-art performance across multiple benchmarks.
  arXiv  Detail & Related papers  (2026-04-21T07:29:55Z)
• AgentSZZ: Teaching the LLM Agent to Play Detective with Bug-Inducing Commits [14.213358505741105]
  AgentSZZ is an agent-based framework for identifying bug-inducing commits.<n>Unlike prior methods, AgentSZZ integrates task-specific tools, domain knowledge, and a ReAct-style loop to enable adaptive and causal tracing of bugs.<n>Experiments show that AgentSZZ consistently outperforms state-of-the-art SZZ algorithms across all settings.
  arXiv  Detail & Related papers  (2026-04-03T02:54:02Z)
• Sponge Tool Attack: Stealthy Denial-of-Efficiency against Tool-Augmented Agentic Reasoning [58.432996881401415]
  Recent work augments large language models (LLMs) with external tools to enable agentic reasoning.<n>We propose Sponge Tool Attack (STA), which disrupts agentic reasoning solely by rewriting the input prompt.<n>STA generates benign-looking prompt rewrites from the original one with high semantic fidelity.
  arXiv  Detail & Related papers  (2026-01-24T19:36:51Z)
• Explainable and Fine-Grained Safeguarding of LLM Multi-Agent Systems via Bi-Level Graph Anomaly Detection [76.91230292971115]
  Large language model (LLM)-based multi-agent systems (MAS) have shown strong capabilities in solving complex tasks.<n>XG-Guard is an explainable and fine-grained safeguarding framework for detecting malicious agents in MAS.
  arXiv  Detail & Related papers  (2025-12-21T13:46:36Z)
• The Trojan Knowledge: Bypassing Commercial LLM Guardrails via Harmless Prompt Weaving and Adaptive Tree Search [58.8834056209347]
  Large language models (LLMs) remain vulnerable to jailbreak attacks that bypass safety guardrails to elicit harmful outputs.<n>We introduce the Correlated Knowledge Attack Agent (CKA-Agent), a dynamic framework that reframes jailbreaking as an adaptive, tree-structured exploration of the target model's knowledge base.
  arXiv  Detail & Related papers  (2025-12-01T07:05:23Z)
• VulAgent: Hypothesis-Validation based Multi-Agent Vulnerability Detection [55.957275374847484]
  VulAgent is a multi-agent vulnerability detection framework based on hypothesis validation.<n>It implements a semantics-sensitive, multi-view detection pipeline, each aligned to a specific analysis perspective.<n>On average, VulAgent improves overall accuracy by 6.6%, increases the correct identification rate of vulnerable--fixed code pairs by up to 450%, and reduces the false positive rate by about 36%.
  arXiv  Detail & Related papers  (2025-09-15T02:25:38Z)
• LLAMA: Multi-Feedback Smart Contract Fuzzing Framework with LLM-Guided Seed Generation [56.84049855266145]
  We propose a Multi-feedback Smart Contract Fuzzing framework (LLAMA) that integrates evolutionary mutation strategies, and hybrid testing techniques.<n>LLAMA achieves 91% instruction coverage and 90% branch coverage, while detecting 132 out of 148 known vulnerabilities.<n>These results highlight LLAMA's effectiveness, adaptability, and practicality in real-world smart contract security testing scenarios.
  arXiv  Detail & Related papers  (2025-07-16T09:46:58Z)
• AgentVigil: Generic Black-Box Red-teaming for Indirect Prompt Injection against LLM Agents [54.29555239363013]
  We propose a generic black-box fuzzing framework, AgentVigil, to automatically discover and exploit indirect prompt injection vulnerabilities.<n>We evaluate AgentVigil on two public benchmarks, AgentDojo and VWA-adv, where it achieves 71% and 70% success rates against agents based on o3-mini and GPT-4o.<n>We apply our attacks in real-world environments, successfully misleading agents to navigate to arbitrary URLs, including malicious sites.
  arXiv  Detail & Related papers  (2025-05-09T07:40:17Z)
• LLM4SZZ: Enhancing SZZ Algorithm with Context-Enhanced Assessment on Large Language Models [10.525352489242398]
  The SZZ algorithm is the dominant technique for identifying bug-inducing commits.<n>It serves as a foundation for many software engineering studies, such as bug prediction and static code analysis.<n>Recently, a deep learning-based SZZ algorithm has been introduced to enhance the original SZZ algorithm.
  arXiv  Detail & Related papers  (2025-04-02T06:40:57Z)
• Improving Discovery of Known Software Vulnerability For Enhanced Cybersecurity [0.0]
  Vulnerability detection relies on standardized identifiers such as Common Platformion (CPE) strings.<n>Non-standardized CPE strings issued by software vendors create a significant challenge.<n>Inconsistent naming conventions, and versioning practices lead to mismatches when querying databases.
  arXiv  Detail & Related papers  (2024-12-21T12:43:52Z)
• VERCATION: Precise Vulnerable Open-source Software Version Identification based on Static Analysis and LLM [12.706661324384319]
  Open-source software (OSS) has experienced a surge in popularity, attributed to its collaborative development model and cost-effective nature.<n>The adoption of specific software versions in development projects may introduce security risks when these versions bring along vulnerabilities.<n>This paper presents VERCATION, an approach designed to identify vulnerable versions of OSS written in C/C++.
  arXiv  Detail & Related papers  (2024-08-14T06:43:06Z)
• Silent Vulnerability-fixing Commit Identification Based on Graph Neural Networks [4.837912059099674]
  VFFINDER is a graph-based approach for automated silent vulnerability fix identification. VFFINDER distinguishes vulnerability-fixing commits from non-fixing ones using attention-based graph neural network models. Our results show that VFFINDER significantly improves the state-of-the-art methods by 272-420% in Precision, 22-70% in Recall, and 3.2X-8.2X in F1.
  arXiv  Detail & Related papers  (2023-09-15T07:51:39Z)

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.