Lecture: "A causal analysis of Harm"

Professor Joseph Halpern is the ​2023/2024 Lowy Distinguished Guest Professor of the Mortimer and Raymond Sackler Institute of Advanced Studies.

Abstract:

It has proved notoriously difficult to define harm.  Indeed, it has been claimed that the notion of harm is a "Frankensteinian jumble" that should be replaced by other well-behaved notions.  On the other hand, harm has become increasingly important as concerns about the potential harm that may be caused by AI systems grow.  For example, the European Union's draft AI act mentions "harm" over 25 times and points out that, given its crucial role, it must be defined carefully.

I start by defining a qualitative notion of harm that uses causal models and is based on a well-known definition of actual causality.  The key features of the definition are that it is based on contrastive causation and uses a default utility to which the utility of actual outcomes is compared.  I show that our definition is able to handle the problematic examples from the literature. I extend the definition to a quantitative notion of harm, first in the case of a single individual, and then for groups of individuals. I show that the ``obvious'' way of doing this (just taking the expected harm for an individual and then summing the expected harm over all individuals) can lead to counterintuitive or inappropriate answers, and discuss alternatives, drawing on work from the decision-theory literature.

 
This is joint work with Sander Beckers and Hana Chockler.