XHXinyi Hou

Xinyi Hou

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Xinyi Hou has a total of 20 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Software Engineering for Large Language Models: Research Status, Challenges, and the Road Ahead

    by Hongzhou Rao, Yanjie Zhao, Xinyi Hou, Shenao Wang, Haoyu Wang

    The rapid advancement of large language models (LLMs) has redefined artificial intelligence (AI), pushing the boundaries of AI research and enabling unbounded possibilities for both academia and industry. However, LLM development faces increasingly complex challenges throughout its lifecycle, while existing research has not systematically investigated these challenges and solutions from the perspective of software engineering (SE) approaches. To fill the gap, we systematically analyze the research status throughout the LLM development lifecycle, which is divided into six phases: requirements engineering, dataset construction, model development and enhancement, testing and evaluation, deployment and operations, and maintenance and evolution. We conclude by identifying the key challenges in each phase and presenting potential research directions to address them. In general, we provide valuable insights from an SE perspective to facilitate future advances in LLM development.

  • Open Access

    Mapping the Landscape of LLM Deployment in the Wild: Prevalence, Patterns, and Perils

    by Xinyi Hou, Jiahao Han, Yanjie Zhao, Shenao Wang, Haoyu Wang

    Large language models (LLMs) are increasingly deployed through open-source and commercial frameworks, enabling individuals and organizations to self-host advanced LLM capabilities. As LLM deployments become prevalent, ensuring their secure and reliable operation has become a critical issue. However, insecure defaults and misconfigurations often expose LLM services to the public internet, posing serious security risks. This study conducted a large-scale empirical investigation of public-facing LLM deployments, focusing on the prevalence of services, exposure characteristics, systemic vulnerabilities, and associated risks. Through internet-wide measurements, we identified 320,102 public-facing LLM services across 15 frameworks and extracted 158 unique API endpoints, categorized into 12 groups based on functionality and security risk. Our analysis found that over 40% of endpoints used plain HTTP, and over 210,000 endpoints lacked valid TLS metadata. API exposure was highly inconsistent: some frameworks, such as Ollama, responded to over 35% of unauthenticated API requests, with about 15% leaking model or system information, while other frameworks implemented stricter controls. We observed widespread use of insecure protocols, poor TLS configurations, and unauthenticated access to critical operations. These security risks, such as model leakage, system compromise, and unauthorized access, are pervasive and highlight the need for a secure-by-default framework and stronger deployment practices.

  • Open Access

    Understanding Bugs in Vector Database Management Systems

    by Yinglin Xie, Xinyi Hou, Yanjie Zhao, Shenao Wang, Kai Chen, Haoyu Wang

  • Open Access

    Mapping the Landscape of LLM Deployment in the Wild: Prevalence, Patterns, and Perils

    by Xinyi Hou, Jiahao Han, Yanjie Zhao, Shenao Wang, Haoyu Wang

    Large language models (LLMs) are increasingly deployed through open-source and commercial frameworks, enabling individuals and organizations to self-host advanced LLM capabilities. As LLM deployments become prevalent, ensuring their secure and reliable operation has become a critical issue. However, insecure defaults and misconfigurations often expose LLM services to the public internet, posing serious security risks. This study conducted a large-scale empirical investigation of public-facing LLM deployments, focusing on the prevalence of services, exposure characteristics, systemic vulnerabilities, and associated risks. Through internet-wide measurements, we identified 320,102 public-facing LLM services across 15 frameworks and extracted 158 unique API endpoints, categorized into 12 groups based on functionality and security risk. Our analysis found that over 40% of endpoints used plain HTTP, and over 210,000 endpoints lacked valid TLS metadata. API exposure was highly inconsistent: some frameworks, such as Ollama, responded to over 35% of unauthenticated API requests, with about 15% leaking model or system information, while other frameworks implemented stricter controls. We observed widespread use of insecure protocols, poor TLS configurations, and unauthenticated access to critical operations. These security risks, such as model leakage, system compromise, and unauthorized access, are pervasive and highlight the need for a secure-by-default framework and stronger deployment practices.

  • Open Access

    TaintP2X: Detecting Taint-Style Prompt-to-Anything Injection Vulnerabilities in LLM-Integrated Applications

    by Junjie He, Shenao Wang, Yanjie Zhao, Xinyi Hou, Zhao Liu, Quanchen Zou, Haoyu Wang

    Large Language Models (LLMs) have revolutionized numerous domains, enabling the development of LLM-integrated applications that autonomously plan and act through tool calling. While these applications demonstrate remarkable capabilities, their ability to invoke sensitive operations, such as file system interactions, code execution, and database queries, introduces critical security risks. In particular, prompt injection vulnerabilities, combined with security-sensitive sink functions, can lead to a broad class of attacks we define as Prompt-to-Anything Injection (P2Xi). These vulnerabilities, stemming from the misuse of LLM-generated outputs without proper validation, can result in severe consequences such as Remote Command Execution (RCE), file injection, SQL injection, and Server-Side Request Forgery (SSRF). To address this emerging threat, we propose TaintP2X, a novel static taint analysis framework that models LLM-generated outputs as taint sources, tracks their propagation through sensitive sink functions, and employs LLM-assisted analysis to prune false positives. TaintP2X achieves high precision and scalability, systematically identifying P2Xi vulnerabilities. In evaluations, TaintP2X demonstrated a 77.1% recall on a ground truth dataset of 35 P2Xi vulnerabilities, outperforming state-of-the-art methods. With TaintP2X, we have uncovered 101 taint paths across 75 open source repositories, with 7 vulnerabilities confirmed by developers, and 5 of them fixed. These findings highlight the prevalence and impact of P2Xi vulnerabilities and establish TaintP2X as a practical solution for securing LLM-integrated ecosystems.


  • Open Access

    Mapping the Landscape of LLM Deployment in the Wild: Prevalence, Patterns, and Perils

    by Xinyi Hou, Jiahao Han, Yanjie Zhao, Shenao Wang, Haoyu Wang

    Large language models (LLMs) are increasingly deployed through open-source and commercial frameworks, enabling individuals and organizations to self-host advanced LLM capabilities. As LLM deployments become prevalent, ensuring their secure and reliable operation has become a critical issue. However, insecure defaults and misconfigurations often expose LLM services to the public internet, posing serious security risks. This study conducted a large-scale empirical investigation of public-facing LLM deployments, focusing on the prevalence of services, exposure characteristics, systemic vulnerabilities, and associated risks. Through internet-wide measurements, we identified 320,102 public-facing LLM services across 15 frameworks and extracted 158 unique API endpoints, categorized into 12 groups based on functionality and security risk. Our analysis found that over 40% of endpoints used plain HTTP, and over 210,000 endpoints lacked valid TLS metadata. API exposure was highly inconsistent: some frameworks, such as Ollama, responded to over 35% of unauthenticated API requests, with about 15% leaking model or system information, while other frameworks implemented stricter controls. We observed widespread use of insecure protocols, poor TLS configurations, and unauthenticated access to critical operations. These security risks, such as model leakage, system compromise, and unauthorized access, are pervasive and highlight the need for a secure-by-default framework and stronger deployment practices.


  • Top Cited Papers
    Open Access

    Model Context Protocol (MCP): Landscape, Security Threats, and Future Research Directions

    by Xinyi Hou, Yanjie Zhao, Shenao Wang, Haoyu Wang

    The Model Context Protocol (MCP) is an emerging open standard that defines a unified, bi-directional communication and dynamic discovery protocol between AI models and external tools or resources, aiming to enhance interoperability and reduce fragmentation across diverse systems. This paper conducts a systematic study of MCP from both architectural and security perspectives. We first define the full lifecycle of an MCP server, comprising four phases (creation, deployment, operation, and maintenance), further decomposed into 16 key activities that capture its functional evolution. Building on this lifecycle analysis, we construct a comprehensive threat taxonomy that categorizes security and privacy risks across four major attacker types: malicious developers, external attackers, malicious users, and security flaws, encompassing 16 distinct threat scenarios. To validate these risks, we develop and analyze real-world case studies that demonstrate concrete attack surfaces and vulnerability manifestations within MCP implementations. Based on these findings, the paper proposes a set of fine-grained, actionable security safeguards tailored to each lifecycle phase and threat category, offering practical guidance for secure MCP adoption. We also analyze the current MCP landscape, covering industry adoption, integration patterns, and supporting tools, to identify its technological strengths as well as existing limitations that constrain broader deployment. Finally, we outline future research and development directions aimed at strengthening MCP’s standardization, trust boundaries, and sustainable growth within the evolving ecosystem of tool-augmented AI systems. All collected data and implementation examples are publicly available at https://github.com/security-pride/MCP_Landscape .


  • Open Access

    LLM App Squatting and Cloning

    by Yinglin Xie, Xinyi Hou, Yanjie Zhao, Kai Chen, Haoyu Wang


  • Open Access

    GPT Store Mining and Analysis

    by Dongxun Su, Yanjie Zhao, Xinyi Hou, Shenao Wang, Haoyu Wang


  • Top Cited Papers
    Open Access

    DeclarUI: Bridging Design and Development with Automated Declarative UI Code Generation

    by Ting Zhou, Yanjie Zhao, Xinyi Hou, Xiaoyu Sun, Kai Chen, Haoyu Wang

    Declarative UI frameworks have gained widespread adoption in mobile app development, offering benefits such as improved code readability and easier maintenance. Despite these advantages, the process of translating UI designs into functional code remains challenging and time-consuming. Recent advancements in multimodal large language models (MLLMs) have shown promise in directly generating mobile app code from user interface (UI) designs. However, the direct application of MLLMs to this task is limited by challenges in accurately recognizing UI components and comprehensively capturing interaction logic. To address these challenges, we propose DeclarUI, an automated approach that synergizes computer vision (CV), MLLMs, and iterative compiler-driven optimization to generate and refine declarative UI code from designs. DeclarUI enhances visual fidelity, functional completeness, and code quality through precise component segmentation, Page Transition Graphs (PTGs) for modeling complex inter-page relationships, and iterative optimization. In our evaluation, DeclarUI outperforms baselines on React Native, a widely adopted declarative UI framework, achieving a 96.8% PTG coverage rate and a 98% compilation success rate. Notably, DeclarUI demonstrates significant improvements over state-of-the-art MLLMs, with a 123% increase in PTG coverage rate, up to 55% enhancement in visual similarity scores, and a 29% boost in compilation success rate. We further demonstrate DeclarUI’s generalizability through successful applications to Flutter and ArkUI frameworks. User studies with professional developers confirm that DeclarUI’s generated code meets industrial-grade standards in code availability, modification time, readability, and maintainability. By streamlining app development, improving efficiency, and fostering designer-developer collaboration, DeclarUI offers a practical solution to the persistent challenges in mobile UI development.