Related papers: A Logical Method for Policy Enforcement over Evolv…
Large Language Model (LLM) agents hold promise for a flexible and scalable alternative to traditional business process automation, but struggle to reliably follow complex company policies. In this study we introduce a deterministic,…
We propose a novel logic, called Frame Logic (FL), that extends first-order logic (with recursive definitions) using a construct Sp(.) that captures the implicit supports of formulas -- the precise subset of the universe upon which their…
We are currently unable to specify human goals and societal values in a way that reliably directs AI behavior. Law-making and legal interpretation form a computational engine that converts opaque human values into legible directives. "Law…
We analyse so-called computable laws, i.e., laws that can be enforced by automatic procedures. These laws should be logically perfect and unambiguous, but sometimes they are not. We use a regulation on road transport to illustrate this…
Specifying legal requirements for software systems to ensure their compliance with the applicable regulations is a major concern to requirements engineering (RE). Personal data which is collected by an organization is often shared with…
While policy-based reinforcement learning (RL) achieves tremendous successes in practice, it is significantly less understood in theory, especially compared with value-based RL. In particular, it remains elusive how to design a provably…
The audit log is a crucial component to monitor fine-grained operations over sensitive data (e.g., personal, health) for security inspection and assurance. Since such data operations can be highly sensitive, it is vital to ensure that the…
When designing agents for operation in uncertain environments, designers need tools to automatically reason about what agents ought to do, how that conflicts with what is actually happening, and how a policy might be modified to remove the…
Software applications are designed to assist users in conducting a wide range of tasks or interactions. They have become prevalent and play an integral part in people's lives in this digital era. To use those software applications, users…
Chase algorithms are indispensable in the domain of knowledge base querying, which enable the extraction of implicit knowledge from a given database via applications of rules from a given ontology. Such algorithms have proved beneficial in…
Natural Language Processing (NLP) is an essential subset of artificial intelligence. It has become effective in several domains, such as healthcare, finance, and media, to identify perceptions, opinions, and misuse, among others. Privacy is…
Large Language Models (LLMs) are increasingly being used for automated evaluations and explaining them. However, concerns about explanation quality, consistency, and hallucinations remain open research challenges, particularly in…
As algorithms become an influential component of government decision-making around the world, policymakers have debated how governments can attain the benefits of algorithms while preventing the harms of algorithms. One mechanism that has…
During the past decade, differential privacy has become the gold standard for protecting the privacy of individuals. However, verifying that a particular program provides differential privacy often remains a manual task to be completed by…
As autonomous AI agents are used in regulated and safety-critical settings, organizations need effective ways to turn policy into enforceable controls. We introduce a regulatory machine learning framework that converts unstructured design…
Privacy policies define the terms under which personal data may be collected and processed by data controllers. The General Data Protection Regulation (GDPR) imposes requirements on these policies that are often difficult to implement.…
Existing and planned legislation stipulates various obligations to provide information about machine learning algorithms and their functioning, often interpreted as obligations to "explain". Many researchers suggest using post-hoc…
Recent advances in learning-based robot manipulation have produced policies with remarkable capabilities. Yet, reliability at deployment remains a fundamental barrier to real-world use, where distribution shift, compounding errors, and…
The proliferation of AI agents, with their complex and context-dependent actions, renders conventional privacy paradigms obsolete. This position paper argues that the current model of privacy management, rooted in a user's unilateral…
Information flow properties express the capability for an agent to infer information about secret behaviours of a partially observable system. In a language-theoretic setting, where the system behaviour is described by a language, we define…