arXiv subjects

Xinming Ou

Publications and source records attributed to Xinming Ou.

10 recordsLinked to original sources

arXiv2026

It is Not Yet Another Tool: Creating and Deploying an Agentic AI Companion in a Security Operations Center

Security Operations Centers (SOCs) process large amounts of tickets, most of which are low-interest events not worthy of further investigation. The repetitive nature of this task and similarity of the vast amounts of tickets make it a prime candidate for generative AI-based automation. We created and deployed an agentic AI companion utilizing large language models through fieldwork within a SOC for over one year. The design of the SOC AI companion was driven by researchers' participation and interactions within the SOC's daily work. SOC analysts were invited to use it during the last four months of the fieldwork. We analyzed the analysts' usage of the companion and found that in more than 90% of the cases the companion's outputs were reused by analysts in the ticket's closing report. Our results showed that when designed "in the trenches" with the intended users, a SOC AI companion can go beyond being yet another tool, but rather a system that co-evolves with its human users as it traverses through the various types of workloads. Analysts naturally started to shape the AI companion's behaviors to fit their particular needs. Our data show that the more human analysts shape the AI companion's behaviors, the more they become comfortable trusting the output from the AI system, resulting in improved productivity.

cs.CR↗

arXiv2026

A Sociotechnical, Practitioner-Centered Approach to Technology Adoption in Cybersecurity Operations: An LLM Case

Technology for security operations centers (SOCs) has a storied history of slow adoption due to concerns about trust and reliability. These concerns are amplified with artificial intelligence, particularly large language models (LLMs), which exhibit issues such as hallucinations and inconsistent outputs. To assess whether LLM-based tools can improve SOC efficiency, we embedded two PhD researchers within a multinational company SOC for six months of ethnographic fieldwork. We identified recurring challenges, such as repetitive tasks, fragmented/unclear data, and tooling bottlenecks, and collaborated directly with practitioners to develop LLM companion tools aligned with their operational needs. Iterative refinement reduced workflow disruption and improved interpretability, leading from skepticism to sustained adoption. Ethnographic analysis indicates that this shift was enabled by our sociotechnical co-creation process consistent with Nonaka's SECI model. This framework explains the common challenges in traditional SOC technology adoption, including workflow misalignment, rigidity against evolving threats and internal requirements, and stagnation over time. Our findings show that the co-creation approach can overcome these old barriers and create a new paradigm for creating usable technology for cybersecurity operations.

cs.CR↗

arXiv2025

Benchmarking Android Malware Detection: Traditional vs. Deep Learning Models

Android malware detection has been extensively studied using both traditional machine learning (ML) and deep learning (DL) approaches. While many state-of-the-art detection models, particularly those based on DL, claim superior performance, they often rely on limited comparisons, lacking comprehensive benchmarking against traditional ML models across diverse datasets. This raises concerns about the robustness of DL-based approaches' performance and the potential oversight of simpler, more efficient ML models. In this paper, we conduct a systematic evaluation of Android malware detection models across four datasets: three recently published, publicly available datasets and a large-scale dataset we systematically collected. We implement a range of traditional ML models, including Random Forests (RF) and CatBoost, alongside advanced DL models such as Capsule Graph Neural Networks (CapsGNN), BERT-based models, and ExcelFormer based models. Our results reveal that in many cases simpler and more computationally efficient ML models achieve comparable or even superior performance compared with DL models. These findings highlight the need for rigorous benchmarking in Android malware detection research. We encourage future studies to conduct more comprehensive benchmarking comparisons between traditional and advanced models to ensure a more accurate assessment of detection capabilities. To facilitate further research, we provide access to our dataset, including app IDs, hash values, and labels.

cs.CR↗

arXiv2025

The Impact of Train-Test Leakage on Machine Learning-based Android Malware Detection

When machine learning is used for Android malware detection, an app needs to be represented in a numerical format for training and testing. We identify a widespread occurrence of distinct Android apps that have identical or nearly identical app representations. In particular, among app samples in the testing dataset, there can be a significant percentage of apps that have an identical or nearly identical representation to an app in the training dataset. This will lead to a data leakage problem that inflates a machine learning model's performance as measured on the testing dataset. The data leakage not only could lead to overly optimistic perceptions on the machine learning models' ability to generalize beyond the data on which they are trained, in some cases it could also lead to qualitatively different conclusions being drawn from the research. We present two case studies to illustrate this impact. In the first case study, the data leakage inflated the performance results but did not impact the overall conclusions made by the researchers in a qualitative way. In the second case study, the data leakage problem would have led to qualitatively different conclusions being drawn from the research. We further examine the real-world impact of the data leakage by dissecting the capability of memorization and the capability of generalization of a machine learning model, and show that by removing leakage from testing data, the evaluation results better reflect the machine learning model's utility in real-world Android malware detection scenarios.

cs.CR↗

arXiv2025

Towards AI-Driven Human-Machine Co-Teaming for Adaptive and Agile Cyber Security Operation Centers

Security Operations Centers (SOCs) face growing challenges in managing cybersecurity threats due to an overwhelming volume of alerts, a shortage of skilled analysts, and poorly integrated tools. Human-AI collaboration offers a promising path to augment the capabilities of SOC analysts while reducing their cognitive overload. To this end, we introduce an AI-driven human-machine co-teaming paradigm that leverages large language models (LLMs) to enhance threat intelligence, alert triage, and incident response workflows. We present a vision in which LLM-based AI agents learn from human analysts the tacit knowledge embedded in SOC operations, enabling the AI agents to improve their performance on SOC tasks through this co-teaming. We invite SOCs to collaborate with us to further develop this process and uncover replicable patterns where human-AI co-teaming yields measurable improvements in SOC productivity.

cs.CR↗

arXiv2024

A Preliminary Study on Using Large Language Models in Software Pentesting

Large language models (LLM) are perceived to offer promising potentials for automating security tasks, such as those found in security operation centers (SOCs). As a first step towards evaluating this perceived potential, we investigate the use of LLMs in software pentesting, where the main task is to automatically identify software security vulnerabilities in source code. We hypothesize that an LLM-based AI agent can be improved over time for a specific security task as human operators interact with it. Such improvement can be made, as a first step, by engineering prompts fed to the LLM based on the responses produced, to include relevant contexts and structures so that the model provides more accurate results. Such engineering efforts become sustainable if the prompts that are engineered to produce better results on current tasks, also produce better results on future unknown tasks. To examine this hypothesis, we utilize the OWASP Benchmark Project 1.2 which contains 2,740 hand-crafted source code test cases containing various types of vulnerabilities. We divide the test cases into training and testing data, where we engineer the prompts based on the training data (only), and evaluate the final system on the testing data. We compare the AI agent's performance on the testing data against the performance of the agent without the prompt engineering. We also compare the AI agent's results against those from SonarQube, a widely used static code analyzer for security testing. We built and tested multiple versions of the AI agent using different off-the-shelf LLMs -- Google's Gemini-pro, as well as OpenAI's GPT-3.5-Turbo and GPT-4-Turbo (with both chat completion and assistant APIs). The results show that using LLMs is a viable approach to build an AI agent for software pentesting that can improve through repeated use and prompt engineering.

cs.CR↗

arXiv2021

What are Attackers after on IoT Devices? An approach based on a multi-phased multi-faceted IoT honeypot ecosystem and data clustering

The growing number of Internet of Things (IoT) devices makes it imperative to be aware of the real-world threats they face in terms of cybersecurity. While honeypots have been historically used as decoy devices to help researchers/organizations gain a better understanding of the dynamic of threats on a network and their impact, IoT devices pose a unique challenge for this purpose due to the variety of devices and their physical connections. In this work, by observing real-world attackers' behavior in a low-interaction honeypot ecosystem, we (1) presented a new approach to creating a multi-phased, multi-faceted honeypot ecosystem, which gradually increases the sophistication of honeypots' interactions with adversaries, (2) designed and developed a low-interaction honeypot for cameras that allowed researchers to gain a deeper understanding of what attackers are targeting, and (3) devised an innovative data analytics method to identify the goals of adversaries. Our honeypots have been active for over three years. We were able to collect increasingly sophisticated attack data in each phase. Furthermore, our data analytics points to the fact that the vast majority of attack activities captured in the honeypots share significant similarity, and can be clustered and grouped to better understand the goals, patterns, and trends of IoT attacks in the wild.

cs.CR↗

arXiv2020

Topology-Aware Hashing for Effective Control Flow Graph Similarity Analysis

Control Flow Graph (CFG) similarity analysis is an essential technique for a variety of security analysis tasks, including malware detection and malware clustering. Even though various algorithms have been developed, existing CFG similarity analysis methods still suffer from limited efficiency, accuracy, and usability. In this paper, we propose a novel fuzzy hashing scheme called topology-aware hashing (TAH) for effective and efficient CFG similarity analysis. Given the CFGs constructed from program binaries, we extract blended n-gram graphical features of the CFGs, encode the graphical features into numeric vectors (called graph signatures), and then measure the graph similarity by comparing the graph signatures. We further employ a fuzzy hashing technique to convert the numeric graph signatures into smaller fixed-size fuzzy hash signatures for efficient similarity calculation. Our comprehensive evaluation demonstrates that TAH is more effective and efficient compared to existing CFG comparison techniques. To demonstrate the applicability of TAH to real-world security analysis tasks, we develop a binary similarity analysis tool based on TAH, and show that it outperforms existing similarity analysis tools while conducting malware clustering.

cs.CR↗

arXiv2020

A First Step Towards Understanding Real-world Attacks on IoT Devices

With the rapid growth of Internet of Things (IoT) devices, it is imperative to proactively understand the real-world cybersecurity threats posed to them. This paper describes our initial efforts towards building a honeypot ecosystem as a means to gathering and analyzing real attack data against IoT devices. A primary condition for a honeypot to yield useful insights is to let attackers believe they are real systems used by humans and organizations. IoT devices pose unique challenges in this respect, due to the large variety of device types and the physical-connectedness nature. We thus create a multiphased approach in building a honeypot ecosystem, where researchers can gradually increase a low-interaction honeypot's sophistication in emulating an IoT device by observing real-world attackers' behaviors. We deployed honeypots both on-premise and in the cloud, with associated analysis and vetting infrastructures to ensure these honeypots cannot be easily identified as such and appear to be real systems. In doing so we were able to attract increasingly sophisticated attack data. We present the design of this honeypot ecosystem and our observation on the attack data so far. Our data shows that real-world attackers are explicitly going after IoT devices, and some captured activities seem to involve direct human interaction (as opposed to scripted automatic activities). We also build a low interaction honeypot for IoT cameras, called Honeycamera, that present to attackers seemingly real videos. This is our first step towards building a more comprehensive honeypot ecosystem that will allow researchers to gain concrete understanding of what attackers are going after on IoT devices, so as to more proactively protect them.

cs.CR↗

arXiv2017

Android Malware Clustering through Malicious Payload Mining

Clustering has been well studied for desktop malware analysis as an effective triage method. Conventional similarity-based clustering techniques, however, cannot be immediately applied to Android malware analysis due to the excessive use of third-party libraries in Android application development and the widespread use of repackaging in malware development. We design and implement an Android malware clustering system through iterative mining of malicious payload and checking whether malware samples share the same version of malicious payload. Our system utilizes a hierarchical clustering technique and an efficient bit-vector format to represent Android apps. Experimental results demonstrate that our clustering approach achieves precision of 0.90 and recall of 0.75 for Android Genome malware dataset, and average precision of 0.98 and recall of 0.96 with respect to manually verified ground-truth.

cs.CR↗