Regulating Algorithmic Harms

Document Type

Article

Publication Date

2024

Abstract

In recent years, the rapid expansion of artificial intelligence (AI) innovations has led to a rise in AI harms—harms emerging from AI operations that pose significant threats to civil rights and democratic values in today’s technological landscape. A facial recognition system for improving criminal detection wrongly collected sensitive personal data and flagged racial minorities as shoplifters. A risk prediction algorithm adopted to identify patients denied medical treatment to Black individuals with poor health conditions. A social media algorithm intended to boost social engagement exacerbated addictive behavior and mental illness in teenagers. These harms are becoming increasingly ubiquitous. Yet, they often manifest in small and invisible forms, enabling them to aggregate while eluding regulatory oversight. Secretly and cumulatively, AI harms affect millions to billions of individuals.

This Article constructs a legal typology to categorize these harms. It argues that there are four primary types of AI harms: eroding privacy, undermining autonomy, diminishing equality, and impairing safety. Additionally, it identifies two aggravating factors—accountability paucity and algorithmic opacity—that cause these seemingly minor harms to escalate into significant problems by obstructing harm detection and correction. This Article then conducts case studies of relevant legal frameworks in the United States, the European Union, and Japan to assess the effectiveness of existing responses to AI harms. The case studies reveal that these regulatory examples are insufficient; they either overlook certain types of harms or fail to consider their cumulative effects, thereby allowing problematic AI practices to circumvent legal obligations.

Drawing on these findings, this Article proposes three legal interventions to address AI harms: each aims to mitigate primary harms by targeting aggravating factors. AI harm assessments, which impose an obligation on AI actors to address the compounded harms, serve as a starting point for enhancing AI accountability. While these assessments often have a collective focus and overlook individual differences, individual rights regarding AI systems provide greater control over AI applications that could lead to aggregated primary harms. The success of these tools relies on AI harm disclosure duties designed to reduce algorithmic opacity in favor of increased harm awareness, especially in situations where AI use is associated with intangible yet far-reaching harms. Taken altogether, this harm-centric procedural approach advances the conversation about the legal definition of AI harms, the boundaries of AI law, and viable approaches to effective AI governance.

Link to Full Text

Share

COinS