Large Language Models (LLMs) have emerged as powerful tools capable of understanding and generating human-like text, offering transformative potential across diverse domains. The Security Operations Center (SOC), responsible for safeguarding digital infrastructure, represents one of these domains. SOCs serve as the frontline of defense in cybersecurity, tasked with continuous monitoring, detection, and response to incidents. However, SOCs face persistent challenges such as high alert volumes, limited resources, high demand for experts with advanced knowledge, delayed response times, and difficulties in leveraging threat intelligence effectively. In this context, LLMs can offer promising solutions by automating log analysis, streamlining triage, improving detection accuracy, and providing the required knowledge in less time. This survey systematically explores the integration of generative AI and more specifically LLMs into SOC workflow, providing a structured perspective on its capabilities, challenges, and future directions. We believe that this survey offers researchers and SOC managers a broad overview of the current state of LLM integration within academic study. To the best of our knowledge, this is the first comprehensive study to examine LLM applications in SOCs in details.

Insider threat detection (ITD) poses a persistent and high-impact challenge in cybersecurity due to the subtle, long-term, and context-dependent nature of malicious insider behaviors. Traditional models often struggle to capture semantic intent and complex behavior dynamics, while existing LLM-based solutions face limitations in prompt adaptability and modality coverage. To bridge this gap, we propose DMFI, a dual-modality framework that integrates semantic inference with behavior-aware fine-tuning. DMFI converts raw logs into two structured views: (1) a semantic view that processes content-rich artifacts (e.g., emails, https) using instruction-formatted prompts; and (2) a behavioral abstraction, constructed via a 4W-guided (When-Where-What-Which) transformation to encode contextual action sequences. Two LoRA-enhanced LLMs are fine-tuned independently, and their outputs are fused via a lightweight MLP-based decision module. We further introduce DMFI-B, a discriminative adaptation strategy that separates normal and abnormal behavior representations, improving robustness under severe class imbalance. Experiments on CERT r4.2 and r5.2 datasets demonstrate that DMFI outperforms state-of-the-art methods in detection accuracy. Our approach combines the semantic reasoning power of LLMs with structured behavior modeling, offering a scalable and effective solution for real-world insider threat detection. Our work demonstrates the effectiveness of combining LLM reasoning with structured behavioral modeling, offering a scalable and deployable solution for modern insider threat detection.

Insider threat detection aims to identify malicious user behavior by analyzing logs that record user interactions. Due to the lack of fine-grained behavior-level annotations, detecting specific behavior-level anomalies within user behavior sequences is challenging. Unsupervised methods face high false positive rates and miss rates due to the inherent ambiguity between normal and anomalous behaviors. In this work, we instead introduce weak labels of behavior sequences, which have lower annotation costs, i.e., the training labels (anomalous or normal) are at sequence-level instead of behavior-level, to enhance the detection capability for behavior-level anomalies by learning discriminative features. To achieve this, we propose a novel framework called Robust Multi-sphere Learning (RMSL). RMSL uses multiple hyper-spheres to represent the normal patterns of behaviors. Initially, a one-class classifier is constructed as a good anomaly-supervision-free starting point. Building on this, using multiple instance learning and adaptive behavior-level self-training debiasing based on model prediction confidence, the framework further refines hyper-spheres and feature representations using weak sequence-level labels. This approach enhances the model's ability to distinguish between normal and anomalous behaviors. Extensive experiments demonstrate that RMSL significantly improves the performance of behavior-level insider threat detection.

--Insider threat detection presents a significant challenge due to the deceptive nature of malicious behaviors, which often resemble legitimate user operations. However, existing approaches typically model system logs as flat event sequences, thereby failing to capture the inherent frequency dynamics and multiscale disturbance patterns embedded in user behavior . T o address these limitations, we propose Log2Sig, a robust anomaly detection framework that transforms user logs into multivariate behavioral frequency signals, introducing a novel representation of user behavior . Log2Sig employs Multivariate V ariational Mode Decomposition (MVMD) to extract Intrinsic Mode Functions (IMFs), which reveal behavioral fluctuations across multiple temporal scales. Based on this, the model further performs joint modeling of behavioral sequences and frequency-decomposed signals: the daily behavior sequences are encoded using a Mamba-based temporal encoder to capture long-term dependencies, while the corresponding frequency components are linearly projected to match the encoder's output dimension. These dual-view representations are then fused to construct a comprehensive user behavior profile, which is fed into a multilayer perceptron for precise anomaly detection. Experimental results on the CERT r4.2 and r5.2 datasets demonstrate that Log2Sig significantly outperforms state-of-the-art baselines in both accuracy and F1 score. Insider threats have emerged as a pressing security issue in enterprise information systems due to their stealthy nature, prolonged attack cycles, and fragmented behavioral patterns.

Enterprises are facing increasing risks of insider threats, while existing detection methods are unable to effectively address these challenges due to reasons such as insufficient temporal dynamic feature modeling, computational efficiency and real-time bottlenecks and cross-modal information island problem. This paper proposes a new insider threat detection framework MambaITD based on the Mamba state space model and cross-modal adaptive fusion. First, the multi-source log preprocessing module aligns heterogeneous data through behavioral sequence encoding, interval smoothing, and statistical feature extraction. Second, the Mamba encoder models long-range dependencies in behavioral and interval sequences, and combines the sequence and statistical information dynamically in combination with the gated feature fusion mechanism. Finally, we propose an adaptive threshold optimization method based on maximizing inter-class variance, which dynamically adjusts the decision threshold by analyzing the probability distribution, effectively identifies anomalies, and alleviates class imbalance and concept drift. Compared with traditional methods, MambaITD shows significant advantages in modeling efficiency and feature fusion capabilities, outperforming Transformer-based methods, and provides a more effective solution for insider threat detection.

Insider threat detection presents unique challenges due to the authorized status of malicious actors and the subtlety of anomalous behaviors. Existing machine learning methods often treat user activity as isolated events, thereby failing to leverage sequential dependencies in user behavior. In this study, we propose a User-Based Sequencing (UBS) methodology, transforming the CERT insider threat dataset into structured temporal sequences suitable for deep sequential modeling. We deploy a Transformer Encoder architecture to model benign user activity and employ its reconstruction errors as anomaly scores. These scores are subsequently evaluated using three unsupervised outlier detection algorithms: One-Class SVM (OCSVM), Local Outlier Factor (LOF), and Isolation Forest (iForest). Across four rigorously designed test sets, including combinations of multiple CERT dataset releases, our UBS-Transformer pipeline consistently achieves state-of-the-art performance - notably 96.61% accuracy, 99.43% recall, 96.38% F1-score, 95.00% AUROC, and exceptionally low false negative (0.0057) and false positive (0.0571) rates. Comparative analyses demonstrate that our approach substantially outperforms tabular and conventional autoencoder baselines, underscoring the efficacy of sequential user modeling and advanced anomaly detection in the insider threat domain.

Internal threat detection (IDT) aims to address security threats within organizations or enterprises by identifying potential or already occurring malicious threats within vast amounts of logs. Although organizations or enterprises have dedicated personnel responsible for reviewing these logs, it is impossible to manually examine all logs entirely.In response to the vast number of logs, we propose a system called RedChronos, which is a Large Language Model-Based Log Analysis System. This system incorporates innovative improvements over previous research by employing Query-Aware Weighted Voting and a Semantic Expansion-based Genetic Algorithm with LLM-driven Mutations. On the public datasets CERT 4.2 and 5.2, RedChronos outperforms or matches existing approaches in terms of accuracy, precision, and detection rate. Moreover, RedChronos reduces the need for manual intervention in security log reviews by approximately 90% in the Xiaohongshu Security Operation Center. Therefore, our RedChronos system demonstrates exceptional performance in handling IDT tasks, providing innovative solutions for these challenges. We believe that future research can continue to enhance the system's performance in IDT tasks while also reducing the response time to internal risk events.

Insider threats usually occur from within the workplace, where the attacker is an entity closely associated with the organization. The sequence of actions the entities take on the resources to which they have access rights allows us to identify the insiders. Insider Threat Detection (ITD) using Machine Learning (ML)-based approaches gained attention in the last few years. However, most techniques employed centralized ML methods to perform such an ITD. Organizations operating from multiple locations cannot contribute to the centralized models as the data is generated from various locations. In particular, the user behavior data, which is the primary source of ITD, cannot be shared among the locations due to privacy concerns. Additionally, the data distributed across various locations result in extreme class imbalance due to the rarity of attacks. Federated Learning (FL), a distributed data modeling paradigm, gained much interest recently. However, FL-enabled ITD is not yet explored, and it still needs research to study the significant issues of its implementation in practical settings. As such, our work investigates an FL-enabled multiclass ITD paradigm that considers non-Independent and Identically Distributed (non-IID) data distribution to detect insider threats from different locations (clients) of an organization. Specifically, we propose a Federated Adversarial Training (FedAT) approach using a generative model to alleviate the extreme data skewness arising from the non-IID data distribution among the clients. Besides, we propose to utilize a Self-normalized Neural Network-based Multi-Layer Perceptron (SNN-MLP) model to improve ITD. We perform comprehensive experiments and compare the results with the benchmarks to manifest the enhanced performance of the proposed FedATdriven ITD scheme.

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.

Enterprises and organizations are faced with potential threats from insider employees that may lead to serious consequences. Previous studies on insider threat detection (ITD) mainly focus on detecting abnormal users or abnormal time periods (e.g., a week or a day). However, a user may have hundreds of thousands of activities in the log, and even within a day there may exist thousands of activities for a user, requiring a high investigation budget to verify abnormal users or activities given the detection results. On the other hand, existing works are mainly post-hoc methods rather than real-time detection, which can not report insider threats in time before they cause loss. In this paper, we conduct the first study towards real-time ITD at activity level, and present a fine-grained and efficient framework LAN. Specifically, LAN simultaneously learns the temporal dependencies within an activity sequence and the relationships between activities across sequences with graph structure learning. Moreover, to mitigate the data imbalance problem in ITD, we propose a novel hybrid prediction loss, which integrates self-supervision signals from normal activities and supervision signals from abnormal activities into a unified loss for anomaly detection. We evaluate the performance of LAN on two widely used datasets, i.e., CERT r4.2 and CERT r5.2. Extensive and comparative experiments demonstrate the superiority of LAN, outperforming 9 state-of-the-art baselines by at least 9.92% and 6.35% in AUC for real-time ITD on CERT r4.2 and r5.2, respectively. Moreover, LAN can be also applied to post-hoc ITD, surpassing 8 competitive baselines by at least 7.70% and 4.03% in AUC on two datasets. Finally, the ablation study, parameter analysis, and compatibility analysis evaluate the impact of each module and hyper-parameter in LAN. The source code can be obtained from https://github.com/Li1Neo/LAN.