Understanding Risks of Privacy Theater with Differential Privacy
Mary Anne Smart, Dhruv Sood, Kristen Vaccaro
摘要
Differential privacy is one of the most popular technologies in the growing area of privacy-conscious data analytics. But differential privacy, along with other privacy-enhancing technologies, may enable privacy theater. In implementations of differential privacy, certain algorithm parameters control the tradeoff between privacy protection for individuals and utility for the data collector; thus, data collectors who do not provide transparency into these parameters may obscure the limited protection offered by their implementation. Through large-scale online surveys, we investigate whether explanations of differential privacy that hide important information about algorithm parameters persuade users to share more browser history data. Surprisingly, we find that the explanations have little effect on individuals' willingness to share data. In fact, most people make up their minds about whether to share before they even learn about the privacy protection.
CCS Concepts: • Human-centered computing → Human computer interaction (HCI); User studies; • Security and privacy → Human and societal aspects of security and privacy; Usability in security and privacy.
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了每一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
引用它的顶会 Paper7
- Don't Look at the Data! How Differential Privacy Reconfigures the Practices of Data ScienceJayshree Sarathy, Sophia Song, Audrey Haque, Tania Schlatter 等CHI 2023 · 被引用 24 次
- Unifying Re-Identification, Attribute Inference, and Data Reconstruction Risks in Differential PrivacyBogdan Kulynych, Juan Felipe Gómez, Georgios Kaissis, Jamie Hayes 等NeurIPS 2025 · 被引用 15 次
- "Having Confidence in My Confidence Intervals": How Data Users Engage with Privacy-Protected Wikipedia DataHarold Triedman, Jayshree Sarathy, Priyanka Nanayakkara, Rachel Cummings 等CHI 2026 · 被引用 2 次
- Comprehension from Chaos: Towards Informed Consent for Private ComputationBailey Kacsmar, Vasisht Duddu, Kyle Tilbury, Blase Ur 等CCS 2023 · 被引用 2 次
- "I inherently just trust that it works": Investigating Mental Models of Open-Source Libraries for Differential PrivacyPatrick Song, Jayshree Sarathy, Michael Shoemate, Salil P. VadhanCSCW 2024 · 被引用 1 次
它引用的顶会 Paper8
- Evaluating Differentially Private Machine Learning in PracticeBargav Jayaraman, David EvansUSENIX Security 2019 · 被引用 586 次
- Auditing Differentially Private Machine Learning: How Private is Private SGD?Matthew Jagielski, Jonathan R. Ullman, Alina OpreaNeurIPS 2020 · 被引用 354 次
- How I Learned to be Secure: a Census-Representative Survey of Security Advice Sources and BehaviorElissa M. Redmiles, Sean Kross, Michelle L. MazurekCCS 2016 · 被引用 192 次
- Informing the Design of a Personalized Privacy Assistant for the Internet of ThingsJessica Colnago, Yuanyuan Feng, Tharangini Palanivel, Sarah Pearman 等CHI 2020 · 被引用 103 次
- "At the End of the Day Facebook Does What ItWants": How Users Experience Contesting Algorithmic Content ModerationKristen Vaccaro, Christian Sandvig, Karrie KarahaliosCSCW 2020 · 被引用 79 次
相关 Paper
- What Are the Chances? Explaining the Epsilon Parameter in Differential PrivacyPriyanka Nanayakkara, Mary Anne Smart, Rachel Cummings, Gabriel Kaptchuk 等USENIX Security 2023
- "I need a better description": An Investigation Into User Expectations For Differential PrivacyRachel Cummings, Gabriel Kaptchuk, Elissa M. RedmilesCCS 2021 · 被引用 45 次
- Towards Effective Differential Privacy Communication for Users' Data Sharing Decision and ComprehensionAiping Xiong, Tianhao Wang, Ninghui Li, Somesh JhaS&P 2020 · 被引用 72 次
- Communicating the Privacy-Utility Trade-off: Supporting Informed Data Donation with Privacy Decision Interfaces for Differential PrivacyDaniel Franzen, Claudia Müller-Birn, Odette WegwarthCSCW 2024 · 被引用 11 次
- The Importance of Being Earnest: Shedding Light on Johnny's (False) Sense of PrivacyWirawan Agahari, Alexandra Dirksen, Martin Johns, Mark de Reuver 等S&P 2025
