Search

The rapid advancements in Large Language Models (LLMs) have revolutionized natural language processing, with GPTs, customized versions of ChatGPT available on the GPT Store, emerging as a prominent technology for specific domains and tasks. To support academic research on GPTs, we introduce GPTZoo, a large-scale dataset comprising 730,420 GPT instances. Each instance includes rich metadata with 21 attributes describing its characteristics, as well as instructions, knowledge files, and third-party services utilized during its development. GPTZoo aims to provide researchers with a comprehensive and readily available resource to study the real-world applications, performance, and potential of GPTs. To facilitate efficient retrieval and analysis of GPTs, we also developed an automated command-line interface (CLI) that supports keyword-based searching of the dataset. To promote open research and innovation, the GPTZoo dataset will undergo continuous updates, and we are granting researchers public access to GPTZoo and its associated tools.

In the digital era, Online Social Networks (OSNs) play a crucial role in information dissemination, with sharing cards for link previews emerging as a key feature. These cards offer snapshots of shared content, including titles, descriptions, and images. In this study, we investigate the construction and dissemination mechanisms of these cards, focusing on two primary server-side generation methods based on Share-SDK and HTML meta tags. Our investigation reveals a novel type of attack, i.e., Sharing Card Forgery (SCF) attack that can be exploited to create forged benign sharing cards for malicious links. We demonstrate the feasibility of these attacks through practical implementations and evaluate their effectiveness across 13 various online social networks. Our findings indicate a significant risk, as the deceptive cards can evade detection and persist on social platforms, thus posing a substantial threat to user security. We also delve into countermeasures and discuss the challenges in effectively mitigating these types of attacks. This study not only sheds light on a novel phishing technique but also calls for heightened awareness and improved defensive strategies in the OSN ecosystem.

As a pivotal extension of the renowned ChatGPT, the GPT Store serves as a dynamic marketplace for various Generative Pre-trained Transformer (GPT) models, shaping the frontier of conversational AI. This paper presents an in-depth measurement study of the GPT Store, with a focus on the categorization of GPTs by topic, factors influencing GPT popularity, and the potential security risks. Our investigation starts with assessing the categorization of GPTs in the GPT Store, analyzing how they are organized by topics, and evaluating the effectiveness of the classification system. We then examine the factors that affect the popularity of specific GPTs, looking into user preferences, algorithmic influences, and market trends. Finally, the study delves into the security risks of the GPT Store, identifying potential threats and evaluating the robustness of existing security measures. This study offers a detailed overview of the GPT Store's current state, shedding light on its operational dynamics and user interaction patterns. Our findings aim to enhance understanding of the GPT ecosystem, providing valuable insights for future research, development, and policy-making in generative AI.

The rapid advancement of Large Language Models (LLMs) has opened up new opportunities for leveraging artificial intelligence in various domains, including cybersecurity. As the volume and sophistication of cyber threats continue to grow, there is an increasing need for intelligent systems that can automatically detect vulnerabilities, analyze malware, and respond to attacks. In this survey, we conduct a comprehensive review of the literature on the application of LLMs in cybersecurity (LLM4Security). By comprehensively collecting over 30K relevant papers and systematically analyzing 127 papers from top security and software engineering venues, we aim to provide a holistic view of how LLMs are being used to solve diverse problems across the cybersecurity domain. Through our analysis, we identify several key findings. First, we observe that LLMs are being applied to a wide range of cybersecurity tasks, including vulnerability detection, malware analysis, network intrusion detection, and phishing detection. Second, we find that the datasets used for training and evaluating LLMs in these tasks are often limited in size and diversity, highlighting the need for more comprehensive and representative datasets. Third, we identify several promising techniques for adapting LLMs to specific cybersecurity domains, such as fine-tuning, transfer learning, and domain-specific pre-training. Finally, we discuss the main challenges and opportunities for future research in LLM4Security, including the need for more interpretable and explainable models, the importance of addressing data privacy and security concerns, and the potential for leveraging LLMs for proactive defense and threat hunting. Overall, our survey provides a comprehensive overview of the current state-of-the-art in LLM4Security and identifies several promising directions for future research., Comment: 46 pages,6 figures

The rapid advancements in pre-trained Large Language Models (LLMs) and Large Multimodal Models (LMMs) have ushered in a new era of intelligent applications, transforming fields ranging from natural language processing to content generation. The LLM supply chain represents a crucial aspect of the contemporary artificial intelligence landscape. It encompasses the entire lifecycle of pre-trained models, from its initial development and training to its final deployment and application in various domains. This paper presents a comprehensive overview of the LLM supply chain, highlighting its three core elements: 1) the model infrastructure, encompassing datasets and toolchain for training, optimization, and deployment; 2) the model lifecycle, covering training, testing, releasing, and ongoing maintenance; and 3) the downstream application ecosystem, enabling the integration of pre-trained models into a wide range of intelligent applications. However, this rapidly evolving field faces numerous challenges across these key components, including data privacy and security, model interpretability and fairness, infrastructure scalability, and regulatory compliance. Addressing these challenges is essential for harnessing the full potential of LLMs and ensuring their ethical and responsible use. This paper provides a future research agenda for the LLM supply chain, aiming at driving the continued advancement and responsible deployment of these transformative LLMs.

The rapid growth and popularity of large language model (LLM) app stores have created new opportunities and challenges for researchers, developers, users, and app store managers. As the LLM app ecosystem continues to evolve, it is crucial to understand the current landscape and identify potential areas for future research and development. This paper presents a forward-looking analysis of LLM app stores, focusing on key aspects such as data mining, security risk identification, development assistance, etc. By examining these aspects, we aim to provide a vision for future research directions and highlight the importance of collaboration among stakeholders to address the challenges and opportunities within the LLM app ecosystem. The insights and recommendations provided in this paper serve as a foundation for driving innovation, ensuring responsible development, and creating a thriving, user-centric LLM app landscape.

The advent of MiniApps, operating within larger SuperApps, has revolutionized user experiences by offering a wide range of services without the need for individual app downloads. However, this convenience has raised significant privacy concerns, as these MiniApps often require access to sensitive data, potentially leading to privacy violations. Our research addresses the critical gaps in the analysis of MiniApps' privacy practices, especially focusing on WeChat MiniApps in the Android ecosystem. Despite existing privacy regulations and platform guidelines, there is a lack of effective mechanisms to safeguard user privacy fully. We introduce MiniScope, a novel two-phase hybrid analysis approach, specifically designed for the MiniApp environment. This approach overcomes the limitations of existing static analysis techniques by incorporating dynamic UI exploration for complete code coverage and accurate privacy practice identification. Our methodology includes modeling UI transition states, resolving cross-package callback control flows, and automated iterative UI exploration. This allows for a comprehensive understanding of MiniApps' privacy practices, addressing the unique challenges of sub-package loading and event-driven callbacks. Our empirical evaluation of over 120K MiniApps using MiniScope demonstrates its effectiveness in identifying privacy inconsistencies. The results reveal significant issues, with 5.7% of MiniApps over-collecting private data and 33.4% overclaiming data collection. These findings emphasize the urgent need for more precise privacy monitoring systems and highlight the responsibility of SuperApp operators to enforce stricter privacy measures.