LLM-Assisted Model-Based Fuzzing of Protocol Implementations

• URL: http://arxiv.org/abs/2508.01750v1
• Date: Sun, 03 Aug 2025 13:16:18 GMT
• Title: LLM-Assisted Model-Based Fuzzing of Protocol Implementations
• Abstract summary: Faults in protocol behavior can lead to vulnerabilities and system failures.<n>A common approach to protocol testing involves constructing Markovian models that capture the state transitions and expected behaviors of the protocol.<n>We propose a novel method that leverages large language models (LLMs) to automatically generate sequences for testing network protocol implementations.
• Score: 9.512044399020514
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Testing network protocol implementations is critical for ensuring the reliability, security, and interoperability of distributed systems. Faults in protocol behavior can lead to vulnerabilities and system failures, especially in real-time and mission-critical applications. A common approach to protocol testing involves constructing Markovian models that capture the state transitions and expected behaviors of the protocol. However, building such models typically requires significant domain expertise and manual effort, making the process time-consuming and difficult to scale across diverse protocols and implementations. We propose a novel method that leverages large language models (LLMs) to automatically generate sequences for testing network protocol implementations. Our approach begins by defining the full set of possible protocol states, from which the LLM selects a subset to model the target implementation. Using this state-based model, we prompt the LLM to generate code that produces sequences of states. This program serves as a protocol-specific sequences generator. The sequences generator then generates test inputs to call the protocol implementation under various conditions. We evaluated our approach on three widely used network protocol implementations and successfully identified 12 previously unknown vulnerabilities. We have reported them to the respective developers for confirmation. This demonstrates the practical effectiveness of our LLM-assisted fuzzing framework in uncovering real-world security issues.

Related papers

• PhyAgentOS: A Self-Evolving Operating System for Embodied Agents with Decoupled Cognitive Planning and Physical Execution [49.776611937968]
  We present PhyAgentOS, a foundation delivering scheduling, verification, memory, benchmarking, and safety as system-level services.<n>Its Session-Centered treats a session, not an action, as the minimum unit of scheduling, compatibility, supervised execution, evidence collection, and acceptance.<n>SessionVerifier distinguishes execution termination from semantic task completion via evidence-grounded verdicts of success, failure, or replan.<n> Benchmarking reuses the deployment session and verification path, so results trace to real execution.
  arXiv  Detail & Related papers  (2026-07-18T04:46:53Z)
• LeanDY: Type-Based and Trace-Based Symbolic Protocol Verification in Lean [9.293322518056357]
  We present an approach that combines type-based reasoning with trace-based reasoning, enabling modular verification of stateful and unbounded protocols.<n>We implement this framework as the LeanDY library for the Lean proof assistant, building on and extending the design of DY*.<n>We formalize SegWit-style blockchain primitives in LeanDY and demonstrate its expressiveness by carrying out an in-depth formalization of payment channels.
  arXiv  Detail & Related papers  (2026-07-03T15:12:30Z)
• A Technical Taxonomy of LLM Agent Communication Protocols [60.76747983053368]
  This study develops a technical taxonomy to classify and analyze large language models (LLMs) agent communication protocols.<n>The framework guides protocol selection and highlights open research gaps such as privacy and policy enforcement.
  arXiv  Detail & Related papers  (2026-06-17T14:45:20Z)
• Agora: Toward Autonomous Bug Detection in Production-Level Consensus Protocols with LLM Agents [11.555840794263753]
  Agora is a domain-aware multi-agent framework that integrates hypothesis-driven testing with LLM capabilities for systematic protocol verification.<n>Our results demonstrate that domain-aware multi-agent collaboration is essential for detecting deep logic bugs in complex protocols.
  arXiv  Detail & Related papers  (2026-05-28T13:27:47Z)
• Autogenesis: A Self-Evolving Agent Protocol [60.15939127351914]
  We introduce Autogenesis Protocol (AGP), a self evolution protocol that decouples what evolves from how evolution occurs.<n>We present Autogenesis System (AGS), a self-evolving multi-agent system that dynamically instantiates, retrieves, and refines protocol-registered resources during execution.
  arXiv  Detail & Related papers  (2026-04-16T14:04:06Z)
• Uncovering Gaps Between RFC Updates and TCP/IP Implementations: LLM-Facilitated Differential Checks on Intermediate Representations [21.889716987837428]
  There are often inconsistencies between the implementation of the protocol stack code and the RFC standard.<n>This inconsistency may not only lead to differences in protocol functions but also cause serious security vulnerabilities.<n>With the rise of large language models, researchers have begun to explore how to extract protocol specifications from RFC documents.
  arXiv  Detail & Related papers  (2025-10-28T13:19:46Z)
• Which LLM Multi-Agent Protocol to Choose? [30.16052895726503]
  We introduce ProtocolBench, a benchmark that compares agent protocols along four measurable axes: task success, end-to-end latency, message or byte overhead, and under failures.<n>On ProtocolBench, protocol choice significantly influences system behavior.<n> Protocol completion is a learnable protocol router that selects per-scenario protocols from requirement and runtime signals.
  arXiv  Detail & Related papers  (2025-10-20T04:53:19Z)
• Rethinking Testing for LLM Applications: Characteristics, Challenges, and a Lightweight Interaction Protocol [83.83217247686402]
  Large Language Models (LLMs) have evolved from simple text generators into complex software systems that integrate retrieval augmentation, tool invocation, and multi-turn interactions.<n>Their inherent non-determinism, dynamism, and context dependence pose fundamental challenges for quality assurance.<n>This paper decomposes LLM applications into a three-layer architecture: textbftextitSystem Shell Layer, textbftextitPrompt Orchestration Layer, and textbftextitLLM Inference Core.
  arXiv  Detail & Related papers  (2025-08-28T13:00:28Z)
• ProtocolLLM: RTL Benchmark for SystemVerilog Generation of Communication Protocols [45.66401695351214]
  We introduce ProtocolLLM, the first benchmark suite specifically targeting widely used SystemVerilog protocols.<n>We observe that most of the models fail to generate SystemVerilog code for communication protocols that follow timing constrains.
  arXiv  Detail & Related papers  (2025-06-09T17:10:47Z)
• ModelForge: Using GenAI to Improve the Development of Security Protocols [1.9241821314180376]
  We introduce ModelForge, a novel tool that automates the translation of protocol specifications.<n>By leveraging advances in Natural Language Processing (NLP) and Generative AI (GenAI), ModelForge processes protocol specifications and generates a CPSA protocol definition.
  arXiv  Detail & Related papers  (2025-06-08T06:27:09Z)
• Training Language Models to Generate Quality Code with Program Analysis Feedback [66.0854002147103]
  Code generation with large language models (LLMs) is increasingly adopted in production but fails to ensure code quality.<n>We propose REAL, a reinforcement learning framework that incentivizes LLMs to generate production-quality code.
  arXiv  Detail & Related papers  (2025-05-28T17:57:47Z)
• CryptoFormalEval: Integrating LLMs and Formal Verification for Automated Cryptographic Protocol Vulnerability Detection [41.94295877935867]
  We introduce a benchmark to assess the ability of Large Language Models to autonomously identify vulnerabilities in new cryptographic protocols. We created a dataset of novel, flawed, communication protocols and designed a method to automatically verify the vulnerabilities found by the AI agents.
  arXiv  Detail & Related papers  (2024-11-20T14:16:55Z)
• Games for AI Control: Models of Safety Evaluations of AI Deployment Protocols [52.40622903199512]
  This paper introduces AI-Control Games, a formal decision-making model of the red-teaming exercise as a multi-objective, partially observable game. We apply our formalism to model, evaluate and synthesise protocols for deploying untrusted language models as programming assistants.
  arXiv  Detail & Related papers  (2024-09-12T12:30:07Z)
• Unleashing the Power of LLM to Infer State Machine from the Protocol Implementation [21.420421792087225]
  We introduce a novel state machine inference approach utilizing Large Language Models (LLMs), named ProtocolGPT.<n>Our method achieves a precision of over 90%, outperforming the baselines by more than 30%.<n> integrating our approach with protocol fuzzing improves coverage by more than 20% and uncovers two 0-day vulnerabilities.
  arXiv  Detail & Related papers  (2024-05-01T08:46:36Z)
• DT-SIM: Property-Based Testing for MPC Security [2.0308771704846245]
  Property-based testing is effective for detecting security bugs in secure protocols. We specifically target Secure Multi-Party Computation (MPC) We devise a test that can detect various flaws in a bit-level implementation of an MPC protocol.
  arXiv  Detail & Related papers  (2024-03-08T02:02:24Z)
• A Survey and Comparative Analysis of Security Properties of CAN Authentication Protocols [92.81385447582882]
  The Controller Area Network (CAN) bus leaves in-vehicle communications inherently non-secure. This paper reviews and compares the 15 most prominent authentication protocols for the CAN bus. We evaluate protocols based on essential operational criteria that contribute to ease of implementation.
  arXiv  Detail & Related papers  (2024-01-19T14:52:04Z)
• OLYMPIA: A Simulation Framework for Evaluating the Concrete Scalability of Secure Aggregation Protocols [1.8069913326395433]
  We present OLYMPIA, a framework for empirical evaluation of secure protocols via simulation. OLYMPIA provides an embedded domain-specific language for defining protocols, and a simulation framework for evaluating their performance.
  arXiv  Detail & Related papers  (2023-02-20T16:46:46Z)
• Towards Semantic Communication Protocols: A Probabilistic Logic Perspective [69.68769942563812]
  We propose a semantic protocol model (SPM) constructed by transforming an NPM into an interpretable symbolic graph written in the probabilistic logic programming language (ProbLog) By leveraging its interpretability and memory-efficiency, we demonstrate several applications such as SPM reconfiguration for collision-avoidance.
  arXiv  Detail & Related papers  (2022-07-08T14:19:36Z)
• Data post-processing for the one-way heterodyne protocol under composable finite-size security [62.997667081978825]
  We study the performance of a practical continuous-variable (CV) quantum key distribution protocol. We focus on the Gaussian-modulated coherent-state protocol with heterodyne detection in a high signal-to-noise ratio regime. This allows us to study the performance for practical implementations of the protocol and optimize the parameters connected to the steps above.
  arXiv  Detail & Related papers  (2022-05-20T12:37:09Z)

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.