REVIEW 11 cited by
Audit-LLM: Multi-Agent Collaboration for Log-based Insider Threat Detection
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Audit-LLM: Multi-Agent Collaboration for Log-based Insider Threat Detection
read the original abstract
Log-based insider threat detection (ITD) detects malicious user activities by auditing log entries. Recently, large language models (LLMs) with strong common sense knowledge have emerged in the domain of ITD. Nevertheless, diverse activity types and overlong log files pose a significant challenge for LLMs in directly discerning malicious ones within myriads of normal activities. Furthermore, the faithfulness hallucination issue from LLMs aggravates its application difficulty in ITD, as the generated conclusion may not align with user commands and activity context. In response to these challenges, we introduce Audit-LLM, a multi-agent log-based insider threat detection framework comprising three collaborative agents: (i) the Decomposer agent, breaking down the complex ITD task into manageable sub-tasks using Chain-of-Thought (COT) reasoning;(ii) the Tool Builder agent, creating reusable tools for sub-tasks to overcome context length limitations in LLMs; and (iii) the Executor agent, generating the final detection conclusion by invoking constructed tools. To enhance conclusion accuracy, we propose a pair-wise Evidence-based Multi-agent Debate (EMAD) mechanism, where two independent Executors iteratively refine their conclusions through reasoning exchange to reach a consensus. Comprehensive experiments conducted on three publicly available ITD datasets-CERT r4.2, CERT r5.2, and PicoDomain-demonstrate the superiority of our method over existing baselines and show that the proposed EMAD significantly improves the faithfulness of explanations generated by LLMs.
Forward citations
Cited by 11 Pith papers
-
LLM4Log: A Systematic Review of Large Language Model-based Log Analysis
LLM4Log is a systematic review of 145 papers on LLM-based log analysis that delivers a unified taxonomy, design patterns, and open challenges for reliable adoption in AIOps.
-
Minos: A Multi-Agent Collaborative Framework for Provenance-Based Backward Tracking
Minos uses a two-tiered multi-agent architecture with retrieval-augmented reasoning and FSM-coordinated agents to reconstruct attack scenarios from provenance data, reporting 0.92 recall and 0.64 precision on 14 scenarios.
-
Benchmarking and Exploring the Capabilities of LLMs for Attack Investigations
AuditBench is a new benchmark of audit logs from 50+ malicious and benign scenarios that evaluates five LLMs on four security investigation tasks and analyzes their performance and error profiles.
-
From Spark to Fire: Modeling and Mitigating Error Cascades in LLM-Based Multi-Agent Collaboration
A graph-based propagation model for error cascades in LLM multi-agent systems plus a genealogy-graph governance plugin that prevents final infection in at least 89% of runs across tested frameworks.
-
Retrieval-Augmented LLMs for Security Incident Analysis
A RAG system with query-based log filtering achieves up to 94% recall in malware incident analysis and 96% attack-step detection, with ablation studies confirming the filtering step is essential.
-
Insight-LLM: LLM-enhanced Multi-view Fusion in Insider Threat Detection
Insight-LLM fuses four behavioral views via Qformer adapters and a LoRA-tuned LLM, reporting state-of-the-art insider threat detection on CERT r4.2/r5.2, with unresolved reporting inconsistencies.
-
ISACL: Internal State Analyzer for Copyrighted Training Data Leakage
An MLP trained on LLM internal states predicts Rouge-L-defined literal copying leakage with high accuracy, but not paraphrase-level leakage.
-
LLM4Log: A Systematic Review of Large Language Model-based Log Analysis
Systematic review of 145 papers on LLM-based log analysis, providing a unified taxonomy, common design patterns, evaluation practices, and challenges for deployment under drift and limited labels.
-
Large Language Models for Security Operations Centers: A Comprehensive Survey
A systematic review of 138 papers classifying LLM applications in SOC workflows by phase, model family, datasets, and maturity.
-
SimViews: An Interactive Multi-Agent System Simulating Visitor-to-Visitor Conversational Patterns to Present Diverse Perspectives of Artifacts in Virtual Museums
The body text belongs to a different paper (Chimera), so the abstract's SimViews claims and its 20-participant study are unsupported in the submitted text.
-
AI-Driven Security Alert Screening and Alert Fatigue Mitigation in Security Operations Centers: A Comprehensive Survey
A literature survey synthesizes 119 studies on AI-driven alert screening into a four-stage taxonomy of filtering, triage, correlation, and generative augmentation while identifying gaps in deployment realism and robustness.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.