Related papers: CitySpec with Shield: A Secure Intelligent Assista…
An increasing number of monitoring systems have been developed in smart cities to ensure that real-time operations of a city satisfy safety and performance requirements. However, many existing city requirements are written in English with…
As more and more monitoring systems have been deployed to smart cities, there comes a higher demand for converting new human-specified requirements to machine-understandable formal specifications automatically. However, these human-specific…
A major challenge to deploying cyber-physical systems with learning-enabled controllers is to ensure their safety, especially in the face of changing environments that necessitate runtime knowledge acquisition. Model-checking and automated…
Logical specifications have been shown to help reinforcement learning algorithms in achieving complex tasks. However, when a task is under-specified, agents might fail to learn useful policies. In this work, we explore the possibility of…
Visual understanding of complex urban street scenes is an enabling factor for a wide range of applications. Object detection has benefited enormously from large-scale datasets, especially in the context of deep learning. For semantic urban…
The increasing adoption of neural networks in learning-augmented systems highlights the importance of model safety and robustness, particularly in safety-critical domains. Despite progress in the formal verification of neural networks,…
The complexity of browsers has steadily increased over the years, driven by the continuous introduction and update of Web platform components, such as novel Web APIs and security mechanisms. Their specifications are manually reviewed by…
This paper targets control problems that exhibit specific safety and performance requirements. In particular, the aim is to ensure that an agent, operating under uncertainty, will at runtime strictly adhere to such requirements. Previous…
Agents built on LLMs are increasingly deployed across diverse domains, automating complex decision-making and task execution. However, their autonomy introduces safety risks, including security vulnerabilities, legal violations, and…
AI-generated speech is becoming increasingly used in everyday life, powering virtual assistants, accessibility tools, and other applications. However, it is also being exploited for malicious purposes such as impersonation, misinformation,…
With the development of the Internet of Things, millions of sensors are being deployed in cities to collect real-time data. This leads to a need for checking city states against city requirements at runtime. In this paper, we develop a…
Formal methods provide very powerful tools and techniques for the design and analysis of complex systems. Their practical application remains however limited, due to the widely accepted belief that formal methods require extensive expertise…
Enhancing word usage is a desired feature for writing assistance. To further advance research in this area, this paper introduces "Smart Word Suggestions" (SWS) task and benchmark. Unlike other works, SWS emphasizes end-to-end evaluation…
Text-to-SQL enables natural access to databases, yet most benchmarks are English-only, limiting multilingual progress. We introduce MultiSpider 2.0, extending Spider 2.0 to eight languages (English, German, French, Spanish, Portuguese,…
Formal verification provides a rigorous and systematic approach to ensure the correctness and reliability of software systems. Yet, constructing specifications for the full proof relies on domain expertise and non-trivial manpower. In view…
Text-to-SQL semantic parsing is an important NLP task, which greatly facilitates the interaction between users and the database and becomes the key component in many human-computer interaction systems. Much recent progress in text-to-SQL…
As our cities and communities become smarter, the systems that keep us safe, such as traffic control centers, emergency response networks, and public transportation, also become more complex. With this complexity comes a greater risk of…
Automated surveillance is essential for the protection of Critical Infrastructures (CIs) in future Smart Cities. The dynamic environments and bandwidth requirements demand systems that adapt themselves to react when events of interest…
The safety of Large Language Models (LLMs) has gained increasing attention in recent years, but there still lacks a comprehensive approach for detecting safety issues within LLMs' responses in an aligned, customizable and explainable…
Skills have become a practical packaging mechanism for agent instructions, workflows, scripts, and reference materials. In enterprise settings, however, a skill often needs to express more than task guidance: goals, input boundaries,…