Lune

NDSS2026Top-tier venue

An LLM-Driven Fuzzing Framework for Detecting Logic Instruction Bugs in PLCs

Jiaxing Cheng, Ming Zhou, Haining Wang, Xin Chen, Yuncheng Wang, Yibo Qu, Limin Sun

Abstract

—Programmable Logic Controllers (PLCs) automate industrial operations using vendor-supplied logic instruction libraries compiled into device firmware. These libraries may contain security flaws that, when exploited through physical control routines, network-facing services, or PLC runtime subsystems, may lead to privilege violations, memory corruption, or data leakage. This paper presents LogicFuzz, the first fuzzing framework designed specifically to target logic instructions in PLC firmware. LogicFuzz constructs a semantic dependency graph (SDG) that captures both operational semantics and inter-instruction dependencies in PLC code. Leveraging the SDG together with an enable-signal mechanism, LogicFuzz automatically synthesizes instruction-tailored seed programs, significantly reducing manual effort and enabling controlled, resettable fuzzing on real PLC hardware. To uncover bugs conditioned on control-flow triggers (i.e., invocation patterns), LogicFuzz mutates the SDG to diversify instruction-invocation contexts. To expose data-triggered faults, it performs coverage-guided parameter mutation under valid semantic constraints. In addition, LogicFuzz integrates a multi-source oracle that monitors runtime logs, status LEDs, and communication states to detect instruction-level failures during fuzzing. We evaluate LogicFuzz on six production PLCs from three major vendors and uncover 19 instruction-level bugs, including four previously unknown vulnerabilities.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Training language models to follow instructions with human feedback cites Language Models are Few-Shot Learners
Builds onCited byLeft to right by year; the more cited, the higher.

Builds on9

  1. Language Models are Few-Shot LearnersTom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah et al.NeurIPS 2020 · 64,255 citations
  2. Training language models to follow instructions with human feedbackLong Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida et al.NeurIPS 2022 · 24,707 citations
  3. SOK: (State of) The Art of War: Offensive Techniques in Binary AnalysisYan Shoshitaishvili, Ruoyu Wang, Christopher Salls, Nick Stephens et al.S&P 2016 · 1,085 citations
  4. Diane: Identifying Fuzzing Triggers in Apps to Generate Under-constrained Inputs for IoT DevicesNilo Redini, Andrea Continella, Dipanjan Das, Giulio De Pasquale et al.S&P 2021 · 72 citations
  5. APICraft: Fuzz Driver Generation for Closed-source SDK LibrariesCen Zhang, Xingwei Lin, Yuekang Li, Yinxing Xue et al.USENIX Security 2021 · 64 citations

Related papers

  1. ICSFuzz: Manipulating I/Os and Repurposing Binary Code to Enable Instrumented Fuzzing in ICS Control ApplicationsDimitrios Tychalas, Hadjer Benkraouda, Michail ManiatakosUSENIX Security 2021 · 42 citations
  2. ICSQuartz: Scan Cycle-Aware and Vendor-Agnostic Fuzzing for Industrial Control SystemsCorban Villa, Constantine Doumanidis, Hithem Lamri, Prashant Hari Narayan Rajput et al.NDSS 2025
  3. PGFUZZ: Policy-Guided Fuzzing for Robotic VehiclesHyungsub Kim, Muslum Ozgur Ozmen, Antonio Bianchi, Z. Berkay Celik et al.NDSS 2021
  4. Fuzzing the Physical Space: Physics-Aware Testing of Black-Box Industrial Control SystemsBurak Sahin, David Oygenblik, Mingxuan Yao, Yizhi Huang et al.S&P 2026 · 3 citations
  5. CFTCG: Test Case Generation for Simulink Model through Code Based FuzzingZhuo Su, Zehong Yu, Dongyan Wang, Rui Wang et al.DAC 2024 · 1 citation
Dusk over the sea between two cliffs drawn in fine vertical lines