Sample-Efficient LLM-Based Detection of Malicious Web Server Logs with Forensically Explainable Reasoning

This paper presents AuditBench, a new benchmark dataset for evaluating the capabilities of LLMs at investigating security-related system audit logs. We design and use this benchmark to explore the performance of LLMs on four log-investigation tasks that incident response teams commonly perform, ranging from triaging alerts generated by detectors to identifying persistence mechanisms on compromised systems. AuditBench consists of system audit logs collected from Linux and Windows machines, and spans over 50 different security investigation scenarios, including both malicious and benign activity. Using our benchmark, we evaluate and analyze the performance of five frontier LLMs at analyzing audit logs for attack investigations. Our analysis illuminates how LLM performance and error profiles vary according to different design choices, such as differences in model size, data representation, prompt construction, and specific investigation tasks. Additionally, we characterize the quality of the explanations produced by LLMs and the types of errors that models make across our benchmark. Collectively, our work provides a foundation for assessing the capabilities of LLMs for investigating security logs, novel insights for practitioners using LLMs in security operations, and important directions for future research.

Logs are ubiquitous in modern systems. Unfortunately, their unstructured nature in flat sequences limits understanding of execution behaviors, hindering effective anomaly diagnosis. To address this, Krone introduces a novel hierarchical log abstraction that transforms flat log sequences into semantically coherent units across entity, action, and status levels. Building on this abstraction, Krone introduces a hierarchical orchestration framework that decomposes flat log sequences into hierarchical execution units and performs modular detection over them. It executes and optimizes the modular detection tasks across levels, enabling precise anomaly detection, localization, and explanation with selective invocation of LLM-based reasoning. In this work, we present Krone-viz, an interactive visualization system based on Krone, which makes hierarchical log analysis interpretable and actionable for software engineers and system operators. Demonstrated on the widely used HDFS benchmark dataset, Krone-viz supports: 1) examining hierarchical decompositions of flat log sequences, 2) inspecting detection results and abnormal segments identified by Krone with LLM-generated explanations, and 3) reusing, reviewing, and revising knowledge generated by LLMs with human-in-the-loop guardrails. The code of Krone-viz is available at https://github.com/LeiMa0324/KRONE_Demo_official, and we deploy a live demo at https://leima0324.github.io/KRONE_Demo_official.

Multi-stage cyberattacks span system, network, and browser logs. Detecting them requires correlating events across all three sources. Machine learning methods can learn these cross-source patterns, but they need labeled multi-source data. Existing public datasets fall short. Network-only datasets such as CICIDS and UNSW-NB15 miss host and browser activity. Host-focused datasets such as LMDG and CICAPT-IIoT lack browser telemetry. ATLAS includes all three sources but labels events only as malicious or benign, without MITRE Adversarial Tactics, Techniques, and Common Knowledge (ATT&CK) technique granularity. No public dataset combines all three sources with per-entry ATT&CK technique labels. We close the gap by building a multi-source log dataset of 870 sessions (70 attack, 800 benign) and approximately 2.3 million events. We captured system, network, and browser activity simultaneously on Windows endpoints. We labeled malicious events with ATT&CK technique IDs, covering 12 tactics and 53 techniques. We generated all attack data using real tools, including Remote Access Trojan (RAT), Command and Control (C2) tunnels, and cloud exfiltration. To demonstrate learnability, we fine-tuned three Small Language Models (SLMs) (Qwen2.5-1.5B, Llama-3.2-3B, Phi-4-Mini) using Low-Rank Adaptation (LoRA). We compared each against its base variant across ten metrics on two tasks: chunk classification and ATT&CK technique identification. Fine-tuning improved every model on every metric. Chunk classification accuracy rose from approximately 8% in the base variants to between 90% and 97% after fine-tuning. Technique identification remained challenging, with the best exact-match accuracy at 42%, although high partial-match scores show the models captured most of the underlying reasoning.