Title: Consumers' Perceived Privacy Violations in Online Advertising

Abstract: In response to privacy concerns about collecting and using personal data, the online advertising industry has been developing privacy-enhancing technologies (PETs), e.g., under Google's Privacy Sandbox initiative. In this research, we use the dual-privacy framework, which postulates that consumers have intrinsic and instrumental preferences for privacy, to understand consumers' perceived privacy violations (PPVs) for current and proposed online advertising practices. The key idea is that different practices differ in whether individual data leaves the consumer's machine or not and in how they track and target consumers; these affect, respectively, the intrinsic and instrumental components of privacy preferences differently, leading to different PPVs for different practices. We conducted online studies focused on consumers in the United States to elicit PPVs for various advertising practices. Our findings confirm the intuition that tracking and targeting consumers under the industry status quo of behavioral targeting leads to high PPV. New technologies or proposals that ensure that data are kept on the consumer's machine lower PPV relative to behavioral targeting but, importantly, this decrease is small. Furthermore, group-level targeting does not differ significantly from individual-level targeting in reducing PPV. Under contextual targeting, where there is no tracking, PPV is significantly reduced. Interestingly, with respect to PPV, consumers are indifferent between seeing untargeted ads and no ads when they are not being tracked. We find that consumer perceptions of privacy violations under different tracking and targeting practices may differ from what technical definitions suggest. Therefore, rather than relying solely on technical perspectives, a consumer-centric approach to privacy is needed, based on, for instance, the dual-privacy framework.