Privacy policies are crucial in the online ecosystem, defining how services handle user data and adhere to regulations such as GDPR and CCPA. However, their complexity and frequent updates often make them difficult for stakeholders to understand and analyze. Current automated analysis methods, which utilize natural language processing, have limitations. They typically focus on individual tasks and fail to capture the full context of the policies. We propose PolicyLR, a new paradigm that offers a comprehensive machine-readable representation of privacy policies, serving as an all-in-one solution for multiple downstream tasks. PolicyLR converts privacy policies into a machine-readable format using valuations of atomic formulae, allowing for formal definitions of tasks like compliance and consistency. We have developed a compiler that transforms unstructured policy text into this format using off-the-shelf Large Language Models (LLMs). This compiler breaks down the transformation task into a two-stage translation and entailment procedure. This procedure considers the full context of the privacy policy to infer a complex formula, where each formula consists of simpler atomic formulae. The advantage of this model is that PolicyLR is interpretable by design and grounded in segments of the privacy policy. We evaluated the compiler using ToS;DR, a community-annotated privacy policy entailment dataset. Utilizing open-source LLMs, our compiler achieves precision and recall values of 0.91 and 0.88, respectively. Finally, we demonstrate the utility of PolicyLR in three privacy tasks: Policy Compliance, Inconsistency Detection, and Privacy Comparison Shopping.

The rising popularity of neural networks (NNs) in recent years and their increasing prevalence in real-world applications have drawn attention to the importance of their verification. While verification is known to be computationally difficult theoretically, many techniques have been proposed for solving it in practice. It has been observed in the literature that by default neural networks rarely satisfy logical constraints that we want to verify. A good course of action is to train the given NN to satisfy said constraint prior to verifying them. This idea is sometimes referred to as continuous verification, referring to the loop between training and verification. Usually training with constraints is implemented by specifying a translation for a given formal logic language into loss functions. These loss functions are then used to train neural networks. Because for training purposes these functions need to be differentiable, these translations are called differentiable logics (DL). This raises several research questions. What kind of differentiable logics are possible? What difference does a specific choice of DL make in the context of continuous verification? What are the desirable criteria for a DL viewed from the point of view of the resulting loss function? In this extended abstract we will discuss and answer these questions.

Regulation of Multi-Agent Systems (MAS) was a research topic of the past decade and one of these proposals was Electronic Institutions. However, with the recent reformulation of Artificial Neural Networks (ANN) as Deep Learning (DL), Security, Privacy, Ethical and Legal issues regarding the use of DL has raised concerns in the Artificial Intelligence (AI) Community. Now that the Regulation of MAS is almost correctly addressed, we propose the Regulation of ANN as Agent-based Training of a special type of regulated ANN that we call Institutional Neural Network. This paper introduces the former concept and provides $\mathcal{I}$, a language previously used to model and extend Electronic Institutions, as a means to implement and regulate DL.

Computing certain answers is the preferred way of answering queries in scenarios involving incomplete data. This, however, is computationally expensive, so practical systems use efficient techniques based on a particular three-valued logic, even though this often leads to incorrect results. Our goal is to provide a general many-valued framework for correctly approximating certain answers. We do so by defining the semantics of many-valued answers and queries, following the principle that additional knowledge about the input must translate into additional knowledge about the output. This framework lets us compare query outputs and evaluation procedures in terms of their informativeness. For each many-valued logic with a knowledge ordering on its truth values, one can build a syntactic evaluation procedure for all first-order queries, that correctly approximates certain answers; additional truth values are used to refine information about certain answers. For concrete examples, we show that a recently proposed approach fixing some of the inconsistencies of SQL query evaluation is an immediate consequence of our framework, and we further refine it by adding a fourth truth value. We show that no evaluation procedure based on Boolean logic delivers correctness guarantees. Finally, we study the relative power of evaluation procedures based on the informativeness of the answers they produce.

In this paper knowledge representation and inference issues for rule-based systems are discussed. The paper deals with improving the logical calculus of Set Attributive Logic founding an expressive rule language XTT2. Representation extensions are introduced, and practical inference rules provided. The original includes an extended state specification, as well as interpreter design. xamples of rule analysis are given. Visual design tool HQed assuring rule quality is also presented.