Search

Large Language Models (LLMs) have gained unprecedented prominence, achieving widespread adoption across diverse domains and integrating deeply into society. The capability to fine-tune general-purpose LLMs, such as Generative Pre-trained Transformers (GPT), for specific tasks has facilitated the emergence of numerous Custom GPTs. These tailored models are increasingly made available through dedicated marketplaces, such as OpenAI's GPT Store. However, their black-box nature introduces significant safety and compliance risks. In this work, we present a scalable framework for the automated evaluation of Custom GPTs against OpenAI's usage policies, which define the permissible behaviors of these systems. Our framework integrates three core components: (1) automated discovery and data collection of models from the GPT store, (2) a red-teaming prompt generator tailored to specific policy categories and the characteristics of each target GPT, and (3) an LLM-as-a-judge technique to analyze each prompt-response pair for potential policy violations. We validate our framework with a manually annotated ground truth, and evaluate it through a large-scale study with 782 Custom GPTs across three categories: Romantic, Cybersecurity, and Academic GPTs. Our manual annotation process achieved an F1 score of 0.975 in identifying policy violations, confirming the reliability of the framework's assessments. The results reveal that 58.7% of the analyzed models exhibit indications of non-compliance, exposing weaknesses in the GPT store's review and approval processes. Furthermore, our findings indicate that a model's popularity does not correlate with compliance, and non-compliance issues largely stem from behaviors inherited from base models rather than user-driven customizations. We believe this approach is extendable to other chatbot platforms and policy domains, improving LLM-based systems safety.

The number and dynamic nature of web and mobile applications presents significant challenges for assessing their compliance with data protection laws. In this context, symbolic and statistical Natural Language Processing (NLP) techniques have been employed for the automated analysis of these systems' privacy policies. However, these techniques typically require labor-intensive and potentially error-prone manually annotated datasets for training and validation. This research proposes the application of Large Language Models (LLMs) as an alternative for effectively and efficiently extracting privacy practices from privacy policies at scale. Particularly, we leverage well-known LLMs such as ChatGPT and Llama 2, and offer guidance on the optimal design of prompts, parameters, and models, incorporating advanced strategies such as few-shot learning. We further illustrate its capability to detect detailed and varied privacy practices accurately. Using several renowned datasets in the domain as a benchmark, our evaluation validates its exceptional performance, achieving an F1 score exceeding 93%. Besides, it does so with reduced costs, faster processing times, and fewer technical knowledge requirements. Consequently, we advocate for LLM-based solutions as a sound alternative to traditional NLP techniques for the automated analysis of privacy policies at scale.

Privacy policies are long, complex documents that end-users seldom read. Privacy labels aim to ameliorate these issues by providing succinct summaries of salient data practices. In December 2020, Apple began requiring that app developers submit privacy labels describing their apps' data practices. Yet, research suggests that app developers often struggle to do so. In this paper, we automatically identify possible discrepancies between mobile app privacy policies and their privacy labels. Such discrepancies could be indicators of potential privacy compliance issues. We introduce the Automated Privacy Label Analysis System (ATLAS). ATLAS includes three components: a pipeline to systematically retrieve iOS App Store listings and privacy policies; an ensemble-based classifier capable of predicting privacy labels from the text of privacy policies with 91.3% accuracy using state-of-the-art NLP techniques; and a discrepancy analysis mechanism that enables a large-scale privacy analysis of the iOS App Store. Our system has enabled us to analyze 354,725 iOS apps. We find several interesting trends. For example, only 40.3% of apps in the App Store provide easily accessible privacy policies, and only 29.6% of apps provide both accessible privacy policies and privacy labels. Among apps that provide both, 88.0% have at least one possible discrepancy between the text of their privacy policy and their privacy label, which could be indicative of a potential compliance issue. We find that, on average, apps have 5.32 such potential compliance issues. We hope that ATLAS will help app developers, researchers, regulators, and mobile app stores alike. For example, app developers could use our classifier to check for discrepancies between their privacy policies and privacy labels, and regulators could use our system to help review apps at scale for potential compliance issues., Comment: 14 pages, 13 figures

Many studies have exposed the massive collection of personal data in the digital ecosystem through, for instance, websites, mobile apps, or smart devices. This fact goes unnoticed by most users, who are also unaware that the collectors are sharing their personal data with many different organizations around the globe. This paper assesses techniques available in the state of the art to identify the organizations receiving this personal data. Based on our findings, we propose ROI (Receiver Organization Identifier), a fully automated method that combines different techniques to achieve a 95.71% precision score in identifying an organization receiving personal data. We demonstrate our method in the wild by evaluating 10,000 Android apps and exposing the organizations that receive users' personal data., Comment: 23 pages, 10 figures

The General Data Protection Regulation (GDPR) aims to ensure that all personal data processing activities are fair and transparent for the European Union (EU) citizens, regardless of whether these are carried out within the EU or anywhere else. To this end, it sets strict requirements to transfer personal data outside the EU. However, checking these requirements is a daunting task for supervisory authorities, particularly in the mobile app domain due to the huge number of apps available and their dynamic nature. In this paper, we propose a fully automated method to assess the compliance of mobile apps with the GDPR requirements for cross-border personal data transfers. We have applied the method to the top-free 10,080 apps from the Google Play Store. The results reveal that there is still a very significant gap between what app providers and third-party recipients do in practice and what is intended by the GDPR. A substantial 56% of analysed apps are potentially non-compliant with the GDPR cross-border transfer requirements., Comment: Author's copy of the submitted manuscript