Workshop Location

The workshop will be in the Rutherford Rooms in the Core Technology Facility.

Program — Monday, 11 Nov 2024

11:00–12:30
Workshop participants are invited to attend the FMAS Keynote talk by Silvia Lizeth Tapia Tarifa.
12:30–13:30
Lunch
13:30–14:30
Keynote Talk
Understanding Privacy by Formalising It
Marija Slavkovik, University of Bergen
14:30–15:00
Acting for the Right Reasons: Creating Reason-Sensitive Artificial Moral Agents
Kevin Baum et al.
15:00–15:30
Coffee Break
15:30–16:20
From Responsibility, via Indifference, to Recklessness
Michael Fisher
The Need for Formal Specifications of Morally Relevant Information for Algorithmic Decision-Making (short paper)
Marija Slavkovik
16:20
Community Discussion

Keynote Speaker

Understanding Privacy by Formalising It
University of Bergen, Norway
Abstract

In most of the modern societies, there is a broad consensus regarding the need for promoting privacy and thus placing restrictions on technological—including AI—developments to protect people’s right to privacy. In order to meet these expectations on the algorithmic level, first we need to make the concept of privacy and the related or derived rights formally specified. However, the notion of (the right to) privacy is subject to different interpretations. In the context of ethical impact of artificial intelligence, privacy is often discussed as a value eroded by digitization and artificial intelligence. Privacy, however, is not one of the traditional moral values, but rather a social value. There are numerous attempts in the literature on defining privacy, but there is no consensus. The overall privacy situation is made more confusing by the “emerging personal data economy”. The data economy both exploits and drives the need for more specific privacy regulations. Algorithmic processes run faster and are more ubiquitous than human processing capabilities. If privacy were a right to be guaranteed to users of digital technologies, we need to understand its specific scope, motivation and eligible trade-offs. If privacy were a value with which we need to align those algorithmic processes, we need to specify it mathematically to the level that we can construct an algorithm that detects whether privacy is violated. We discuss initial attempts at using a multi-modal logic to provide an initial formalization of different theories and approaches’ basic principles and their implications investigating the right to privacy as an epistemic right within the theory of normative positions.

Marija Slavkovik
Marija Slavkovik
Biography

Marija Slavkovik is a Professor with the Faculty for Social Sciences of the University of Bergen. Her background is in computer science and artificial intelligence. She has been doing research in machine ethics since 2012. Machine ethics studies how moral reasoning can or should be automated. Marija works on formalising ethical collective decision-making. She has held held several seminars, tutorials and graduate courses on AI ethics (https://slavkovik.com/teaching.html). Marija is a vice-chair of the the Norwegian AI Association, board member of European Association for Artificial Intelligence, a member of the informal advisory group on Ethics, Legal, Social Issues (ELS) of CLAIRE, in the editorial board of AI Magazine, and AI and Society track editor of JAIR. She is the current chair of the department of information science and media studies that since 2021 has been offering, in collaboration with the department of informatics the first bachelor program in AI in Norway.

Overview

Recent advances in artificial intelligence have led to a range of concerns about the ethical impact of the technology. This includes concerns about the day-to-day behaviour of robotic systems that will interact with humans in workplaces, homes and hospitals. One of the themes of these concerns is the need for such systems to take ethics into account when reasoning. This has generated new interest in how we can specify, implement and validate ethical reasoning. The aim of this workshop would be to look at formal approaches to these questions. Topics of interest include but are not limited to:

Submission Information

We will accept three types of paper prepared using the EPTCS LaTeX style.

Papers should be submitted using OpenReview. The paper type should be included as part of the paper title. Reviews will be single-blind. Please note that OpenReview can take up to two weeks to approve a new profile registration that does not contain an institution email address.

We intend to host informal workshop proceedings on OpenReview.

Important Dates

Schedule and Location

This will be a half day workshop with informal proceedings, consisting of short talks and opportunities for discussion. The workshop will be in the Rutherford Rooms in the Core Technology Facility.

Program Chair

Louise Dennis, University of Manchester

Program Committee