OpenAI has enabled third-party developers to build applications around ChatGPT, known as GPTs, to expand its capability to handle complex and specialized tasks. A key feature of GPTs is Retrieval-Augmented Generation (RAG), which allows developers to upload documents containing domain knowledge or application context, referred to as file knowledge. However, these documents often contain sensitive information, and the security mechanisms governing access control in GPTs remains an underexplored area.

Virtual personal assistants (VPA) services encompass a large number of third-party applications (or apps) to enrich their functionalities. These apps have been well examined to scrutinize their data collection behaviors against their declared privacy policies. Nonetheless, it is often overlooked that most users tend to ignore privacy policies at the installation time. Dishonest developers thus can exploit this situation by embedding excessive declarations to cover their data collection behaviors during compliance auditing.

ChatGPT has enabled third-party developers to create plugins to expand ChatGPT's capabilities. These plugins are distributed through OpenAI's plugin store, making them easily accessible to users. With ChatGPT as the backbone, this app ecosystem has illustrated great business potential by offering users personalized services in a conversational manner. Nonetheless, many crucial aspects regarding app development, deployment, and security of this ecosystem have yet to be thoroughly studied in the research community, potentially hindering a broader adoption by both developers and users. In this work, we conduct the first comprehensive study of the ChatGPT app ecosystem, aiming to illuminate its landscape for our research community. Our study examines the distribution and deployment models in the integration of LLMs and third-party apps, and assesses their security and privacy implications. We uncover an uneven distribution of functionality among ChatGPT plugins, highlighting prevalent and emerging topics. We also identify severe flaws in the authentication and user data protection for third-party app APIs integrated within LLMs, revealing a concerning status quo of security and privacy in this app ecosystem. Our work provides insights for the secure and sustainable development of this rapidly evolving ecosystem.

Large language models (LLMs) have achieved unprecedented success in the field of natural language processing. However, the black-box nature of their internal mechanisms has brought many concerns about their trustworthiness and interpretability. Recent research has discovered a class of abnormal tokens in the model's vocabulary space and named them "glitch tokens". Those tokens, once included in the input, may induce the model to produce incorrect, irrelevant, or even harmful results, drastically undermining the reliability and practicality of LLMs.

The energy industry is undergoing significant transformations as it strives to achieve net-zero emissions and future-proof its infrastructure, where every participant in the power grid has the potential to both consume and produce energy resources. Federated learning -- which enables multiple participants to collaboratively train a model without aggregating the training data -- becomes a viable technology. However, the global model parameters that have to be shared for optimization are still susceptible to training data leakage. In this work, we propose confined gradient descent (CGD) that enhances the privacy of federated learning by eliminating the sharing of global model parameters. CGD exploits the fact that a gradient descent optimization can start with a set of discrete points and converges to another set in the neighborhood of the global minimum of the objective function. As such, each participant can independently initiate its own private global model~(referred to as the confined model ), and collaboratively learn it towards the optimum. The updates to their own models are worked out in a secure collaborative way during the training process.In such a manner, CGD retains the ability of learning from distributed data but greatly diminishes information sharing. Such a strategy also allows the proprietary confined models to adapt to the heterogeneity in federated learning, providing inherent benefits of fairness. We theoretically and empirically demonstrate that decentralized CGD øne provides a stronger differential privacy (DP) protection; \two is robust against the state-of-the-art poisoning privacy attacks; þree results in bounded fairness guarantee among participants; and \four provides high test accuracy (comparable with centralized learning) with a bounded convergence rate over four real-world datasets.

An app ecosystem built around virtual personal assistant (VPA) services becomes flourishing in recent years, fueled by the booming of the Internet of Things (IoT). A large number of functionality-rich VPA applications (or apps for short) have been released through app stores, and become easily-accessible by users through their smart speakers. In response to the increasingly stringent data protection regulations around the world, VPA service providers require app developers to include a privacy policy that declares their data handling practices. These privacy policies serve as the de facto agreement between developers and users, and may be taken as the basis in resolving conflicts in the event of a data breach. Therefore, it is essential that privacy policy documents are crafted in a clear, easy-to-understand, and unambiguous way. In this work, we conduct the first systematic study on the quality of privacy policies in the VPA app domain. Based on our review of literature and documents from standard working groups, we identify four metrics that enable the quality of the privacy policy to become measurable, including timeliness, availability, completeness and readability. We then develop QuPer, which extracts the meta features (e.g., update history) and linguistic features (e.g., sentence semantics) from privacy policies, and assesses their quality. Our analysis reveals that the status of the quality of privacy policies in the VPA app domain is concerning. For instance, only 1.17% of privacy policies completely cover all contents that are regarded as privacy concerns by legislation (e.g., GDPR article 13) and relevant literature. Our findings are expected to raise an alert among the VPA app developers and provide them with guidelines for creating high-quality privacy policy documents. We also encourage app store operators to implement a vetting process that ensures the quality of privacy policies before apps are released to the public.

When deploying pre-trained neural network models in real-world applications, model consumers often encounter resource-constraint platforms such as mobile and smart devices. They typically use the pruning technique to reduce the size and complexity of the model, generating a lighter one with less resource consumption. Nonetheless, most existing pruning methods are proposed with a premise that the model after being pruned has a chance to be fine-tuned or even retrained based on the original training data. This may be unrealistic in practice, as the data controllers are often reluctant to provide their model consumers with the original data. In this work, we study the neural network pruning in the data-free context, aiming to yield lightweight models that are not only accurate in prediction but also robust against undesired inputs in open-world deployments. Considering the absence of fine-tuning and retraining that can fix the mis-pruned units, we replace the traditional aggressive one-shot strategy with a conservative one that treats model pruning as a progressive process. We propose a pruning method based on stochastic optimization that uses robustness-related metrics to guide the pruning process. Our method is evaluated with a series of experiments on diverse neural network models. The experimental results show that it significantly outperforms existing one-shot data-free pruning approaches in terms of robustness preservation and accuracy.

The ubiquitous deployment of Internet of Things (IoT) devices enhances connectivity and communication, and benefits almost every aspect of our lives from manufacturing to retail to smart homes. However, low levels of security protection in these devices due to their limited resources open opportunities for malicious users. An IoT forensics system collecting, processing, analyzing and reporting evidence of attack is required to mitigate the IoT security issues. Although such system has been studied over the past decade and solutions such as cloud-based IoT forensic were proposed, limitation still exist. In this paper, leveraging on the blockchain technology, we propose a per-missioned blockchain-based IoT forensics framework to enhance the integrity, authenticity and non-repudiation properties for the collected evidence. We formally define the system architecture, provide framework details, and propose a cryptographic-based approach to mitigate identity privacy concern.

Android bytecode is easy to reverse engineer. It has been a common practice for Android application developers to protect their applications with obfuscation techniques. Control flow obfuscation aims to make it more difficult to determine the actual application control flows and thereby impede the understanding of the application logic by the attacker. Despite of the strong potency (i.e., high complexity increment), control flow obfuscation usually incurs a large overhead due to the call and return instructions inserted, which makes the application developer reluctant to use it in practice. In this paper, we present a pragmatic control-flow obfuscation approach where the application developer has more freedom to customize the trade-off between the achieved complexity and overhead. A new subset of application methods will be obfuscated by using a combination of packed-switch and try-catch constructs in different rounds, and larger methods are obfuscated by creating more code fragments in earlier rounds. After each round, the complexity increment will be automatically calculated using our implemented cyclomatic complexity based metric and checked against the target complexity increment. In other words, the obfuscation is conducted in a progressive manner until the target complexity increment is reached. The experimental results show that our method incurs averaged area overhead of 4.07% while achieving almost double complexity increment than the existing method when the same number of application methods are obfuscated.