Search for: All records

Website privacy policies are often lengthy and intricate. Privacy assistants assist in simplifying policies and making them more accessible and user-friendly. The emergence of generative AI (genAI) offers new opportunities to build privacy assistants that can answer users’ questions about privacy policies. However, genAI’s reliability is a concern due to its potential for producing inaccurate information. This study introduces GenAIPABench, a benchmark for evaluating Generative AI-based Privacy Assistants (GenAIPAs). GenAIPABench includes: 1) A set of curated questions about privacy policies along with annotated answers for various organizations and regulations; 2) Metrics to assess the accuracy, relevance, and consistency of responses; and 3) A tool for generating prompts to introduce privacy policies and paraphrased variants of the curated questions. We evaluated 3 leading genAI systems—ChatGPT-4, Bard, and Bing AI—using GenAIPABench to gauge their effectiveness as GenAIPAs. Our results demonstrate significant promise in genAI capabilities in the privacy domain while also highlighting challenges in managing complex queries, ensuring consistency, and verifying source accuracy. 

Smart space administration and application development is challenging in part due to the semantic gap that exists between the high-level requirements of users and the low-level capabilities of IoT devices. The stakeholders in a smart space are required to deal with communicating with specific IoT devices, capturing data, processing it, and abstracting it out to generate useful inferences. Additionally, this makes reusability of smart space applications difficult, since they are developed for specific sensor deployments. In this article, we present a holistic approach to IoT smart spaces, the SemIoTic ecosystem, to facilitate application development, space management, and service provision to its inhabitants. The ecosystem is based on a centralized repository, where developers can advertise their space-agnostic applications, and a SemIoTic system deployed in each smart space that interacts with those applications to provide them with the required information. SemIoTic applications are developed using a metamodel that defines high-level concepts abstracted from the smart space about the space itself and the people within it. Application requirements can be expressed then in terms of user-friendly high-level concepts, which are automatically translated by SemIoTic into sensor/actuator commands adapted to the underlying device deployment in each space. We present a reference implementation of the ecosystem that has been deployed at the University of California, Irvine and is abstracting data from hundreds of sensors in the space and providing applications to campus members. 

Emerging domains, such as sensor-driven smart spaces and social media analytics, require incoming data to be enriched prior to its use. Enrichment often consists of machine learning (ML) functions that are too expensive/infeasible to execute at ingestion. We develop a strategy entitled Just-in-time ENrichmeNt in quERy Processing (JENNER) to support interactive analytics over data as soon as it arrives for such application context. JENNER exploits the inherent tradeoffs of cost and quality often displayed by the ML functions to progressively improve query answers during query execution. We describe how JENNER works for a large class of SPJ and aggregation queries that form the bulk of data analytics workload. Our experimental results on real datasets (IoT and Tweet) show that JENNER achieves progressive answers performing significantly better than the naive strategies of achieving progressive computation.