Large Language Models as Explainable Cyberattack Detectors for Energy Industrial Control Systems

• URL: http://arxiv.org/abs/2604.26079v1
• Date: Tue, 28 Apr 2026 19:44:38 GMT
• Title: Large Language Models as Explainable Cyberattack Detectors for Energy Industrial Control Systems
• Abstract summary: We study whether an off-the-shelf large language model (LLM) can serve as a complementary, human-in-the-loop layer for ICS detectors.<n>We cast this as a binary network-side normal/critical decision task on two public ICS datasets.<n>LLM produces a normal/critical alert together with a concise, token-grounded incident record for analyst review.
• Score: 1.784933900656067
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In modern energy systems, industrial control systems (ICS) and power-system SCADA require intrusion detection that is not only accurate but also auditable by operators. The ICS intrusion-detection landscape is currently dominated by established supervised detectors. In this paper, we study whether an off-the-shelf large language model (LLM) can serve as a complementary, human-in-the-loop layer for Modbus traffic. We cast this as a binary network-side normal/critical decision task on two public ICS Modbus datasets, collapsing attack periods and other safety-critical behaviors into a single critical class. Each Modbus communication instance is converted into a compact token string derived from discretized protocol fields, and a prompt-configured LLM produces a normal/critical alert together with a concise, token-grounded incident record for analyst review. Under matched event information and shared evaluation splits, the resulting LLM-based triage pipeline achieves high predictive performance on both benchmarks and is broadly comparable to strong supervised baselines, while requiring no task-specific weight updates. To assess the audit record, we apply intervention-based diagnostics, including sufficiency- and necessity-style tests, which provide evidence that the cited tokens are often decision-relevant to the model's own prediction. These records are intended as audit signals rather than full human-grounded explanations.

Related papers

• From Detection to Action: Using LLM Agents for Fault-Tolerant Control [0.21313236831585222]
  We propose an agentic Large Language Model (LLM) framework for Fault-Tolerant Control (FTC)<n>It transforms fault detection outputs into constraint-aware recovery actions grounded in plant-specific knowledge.<n>We show that semantically grounded agents can derive valid recovery decisions within latency budgets compatible with the respective process dynamics.
  arXiv  Detail & Related papers  (2026-06-26T12:13:58Z)
• CIAware-Bench: Benchmarking Control Intervention Awareness Across Frontier LLMs [100.38986535324284]
  We introduce textbfCIAware-Bench, a benchmark for measuring textbfcontrol textbfintervention (CI) awareness across frontier models.<n>CIAware-Bench tests whether models can distinguish their own trajectories from those modified by a control intervention.
  arXiv  Detail & Related papers  (2026-06-09T16:24:16Z)
• Monitoring Data-aware Temporal Properties (Extended Version) [56.386411908764494]
  We consider anticipatory monitoring of linear-time properties enriched with an arbitrary SMT theory over finite traces.<n>Anticipatory monitoring in this setting is highly challenging, as the monitoring state depends on both the trace prefix seen so far and all its possible finite continuations.<n>We present and formally prove the correctness of a novel foundational framework for monitoring properties in an expressive fragment offMT.
  arXiv  Detail & Related papers  (2026-05-14T10:23:11Z)
• Scalable Context-Aware Graph Attention for Unsupervised Anomaly Detection in Large-Scale Mobile Networks [0.5219568203653523]
  Anomaly detection framework designed to operate as a single shared model across large populations of network elements.<n>Model combines temporal and feature-wise graph attention with lightweight static and dynamic context conditioning.<n>It produces per-element, per-feature anomaly scores, converted to alerts via fully unsupervised thresholds from validation residuals.
  arXiv  Detail & Related papers  (2026-05-01T07:43:14Z)
• Multi-Agent Collaborative Intrusion Detection for Low-Altitude Economy IoT: An LLM-Enhanced Agentic AI Framework [60.72591149679355]
  The rapid expansion of low-altitude economy Internet of Things (LAE-IoT) networks has created unprecedented security challenges.<n>Traditional intrusion detection systems fail to tackle the unique characteristics of aerial IoT environments.<n>We introduce a large language model (LLM)-enabled agentic AI framework for enhancing intrusion detection in LAE-IoT networks.
  arXiv  Detail & Related papers  (2026-01-25T12:47:25Z)
• zkSTAR: A zero knowledge system for time series attack detection enforcing regulatory compliance in critical infrastructure networks [0.9558392439655014]
  Industrial control systems (ICS) form the operational backbone of critical infrastructure networks.<n>Regulators are imposing stricter compliance requirements to ensure system-wide security and reliability.<n>A central challenge is enabling regulators to verify the effectiveness of detection mechanisms without requiring utilities to disclose sensitive operational data.<n>We introduce zkSTAR, a cyberattack detection framework that leverages zk-SNARKs to reconcile these requirements and enable provable detection guarantees.
  arXiv  Detail & Related papers  (2025-10-27T06:45:11Z)
• Adaptive Attacks on Trusted Monitors Subvert AI Control Protocols [80.68060125494645]
  We study adaptive attacks by an untrusted model that knows the protocol and the monitor model.<n>We instantiate a simple adaptive attack vector by which the attacker embeds publicly known or zero-shot prompt injections in the model outputs.
  arXiv  Detail & Related papers  (2025-10-10T15:12:44Z)
• DRIFT: Dynamic Rule-Based Defense with Injection Isolation for Securing LLM Agents [52.92354372596197]
  Large Language Models (LLMs) are increasingly central to agentic systems due to their strong reasoning and planning capabilities.<n>This interaction also introduces the risk of prompt injection attacks, where malicious inputs from external sources can mislead the agent's behavior.<n>We propose a Dynamic Rule-based Isolation Framework for Trustworthy agentic systems, which enforces both control and data-level constraints.
  arXiv  Detail & Related papers  (2025-06-13T05:01:09Z)
• Interpretable Anomaly Detection in Encrypted Traffic Using SHAP with Machine Learning Models [0.0]
  This study aims to develop an interpretable machine learning-based framework for anomaly detection in encrypted network traffic.<n>Models are trained and evaluated on three benchmark encrypted traffic datasets.<n> SHAP visualizations successfully revealed the most influential traffic features contributing to anomaly predictions.
  arXiv  Detail & Related papers  (2025-05-22T05:50:39Z)
• CANTXSec: A Deterministic Intrusion Detection and Prevention System for CAN Bus Monitoring ECU Activations [53.036288487863786]
  We propose CANTXSec, the first deterministic Intrusion Detection and Prevention system based on physical ECU activations.<n>It detects and prevents classical attacks in the CAN bus, while detecting advanced attacks that have been less investigated in the literature.<n>We prove the effectiveness of our solution on a physical testbed, where we achieve 100% detection accuracy in both classes of attacks while preventing 100% of FIAs.
  arXiv  Detail & Related papers  (2025-05-14T13:37:07Z)
• How Robust Are Router-LLMs? Analysis of the Fragility of LLM Routing Capabilities [62.474732677086855]
  Large language model (LLM) routing has emerged as a crucial strategy for balancing computational costs with performance.<n>We propose the DSC benchmark: Diverse, Simple, and Categorized, an evaluation framework that categorizes router performance across a broad spectrum of query types.
  arXiv  Detail & Related papers  (2025-03-20T19:52:30Z)
• A Framework for the Systematic Assessment of Anomaly Detectors in Time-Sensitive Automotive Networks [0.4077787659104315]
  We present an assessment framework that allows for reproducible, comparable, and rapid evaluation of anomaly detection algorithms. We evaluate exemplary detection mechanisms and reveal how the detection performance is influenced by different combinations of TSN traffic flows and anomaly types.
  arXiv  Detail & Related papers  (2024-05-02T14:29:42Z)
• Unsupervised Continual Anomaly Detection with Contrastively-learned Prompt [80.43623986759691]
  We introduce a novel Unsupervised Continual Anomaly Detection framework called UCAD. The framework equips the UAD with continual learning capability through contrastively-learned prompts. We conduct comprehensive experiments and set the benchmark on unsupervised continual anomaly detection and segmentation.
  arXiv  Detail & Related papers  (2024-01-02T03:37:11Z)
• A Bayesian Framework for Digital Twin-Based Control, Monitoring, and Data Collection in Wireless Systems [35.59201763567714]
  Digital twin (DT) platforms are seen as a promising paradigm to control, monitor, and analyze software-based, "open", communication systems. A key challenge in the deployment of DT systems is to ensure that virtual control optimization, monitoring, and analysis at the DT are safe and reliable. This paper presents a general Bayesian framework with the aim of quantifying and accounting for model uncertainty at the DT.
  arXiv  Detail & Related papers  (2022-12-02T18:13:48Z)

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.