Countering Privacy Nihilism

• URL: http://arxiv.org/abs/2507.18253v1
• Date: Thu, 24 Jul 2025 09:52:18 GMT
• Title: Countering Privacy Nihilism
• Authors: Severin Engelmann, Helen Nissenbaum,
• Abstract summary: AI may be presumed capable of inferring "everything from everything"<n>Discarding data categories as a normative anchoring in privacy and data protection is what we call privacy nihilism.<n>We propose moving away from privacy frameworks that focus solely on data type, neglecting all other factors.
• Score: 2.6212127510234797
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Of growing concern in privacy scholarship is artificial intelligence (AI), as a powerful producer of inferences. Taken to its limits, AI may be presumed capable of inferring "everything from everything," thereby making untenable any normative scheme, including privacy theory and privacy regulation, which rests on protecting privacy based on categories of data - sensitive versus non-sensitive, private versus public. Discarding data categories as a normative anchoring in privacy and data protection as a result of an unconditional acceptance of AI's inferential capacities is what we call privacy nihilism. An ethically reasoned response to AI inferences requires a sober consideration of AI capabilities rather than issuing an epistemic carte blanche. We introduce the notion of conceptual overfitting to expose how privacy nihilism turns a blind eye toward flawed epistemic practices in AI development. Conceptual overfitting refers to the adoption of norms of convenience that simplify the development of AI models by forcing complex constructs to fit data that are conceptually under-representative or even irrelevant. While conceptual overfitting serves as a helpful device to counter normative suggestions grounded in hyperbolic AI capability claims, AI inferences shake any privacy regulation that hinges protections based on restrictions around data categories. We propose moving away from privacy frameworks that focus solely on data type, neglecting all other factors. Theories like contextual integrity evaluate the normative value of privacy across several parameters, including the type of data, the actors involved in sharing it, and the purposes for which the information is used.

Related papers

• Rethinking Data Protection in the (Generative) Artificial Intelligence Era [115.71019708491386]
  We propose a four-level taxonomy that captures the diverse protection needs arising in modern (generative) AI models and systems.<n>Our framework offers a structured understanding of the trade-offs between data utility and control, spanning the entire AI pipeline.
  arXiv  Detail & Related papers  (2025-07-03T02:45:51Z)
• Enforcing Demographic Coherence: A Harms Aware Framework for Reasoning about Private Data Release [14.939460540040459]
  We introduce demographic coherence, a condition inspired by privacy attacks that we argue is necessary for data privacy.<n>Our framework focuses on confidence rated predictors, which can in turn be distilled from almost any data-informed process.<n>We prove that every differentially private data release is also demographically coherent, and that there are demographically coherent algorithms which are not differentially private.
  arXiv  Detail & Related papers  (2025-02-04T20:42:30Z)
• Differential Privacy Overview and Fundamental Techniques [63.0409690498569]
  This chapter is meant to be part of the book "Differential Privacy in Artificial Intelligence: From Theory to Practice" It starts by illustrating various attempts to protect data privacy, emphasizing where and why they failed. It then defines the key actors, tasks, and scopes that make up the domain of privacy-preserving data analysis.
  arXiv  Detail & Related papers  (2024-11-07T13:52:11Z)
• Smoke Screens and Scapegoats: The Reality of General Data Protection Regulation Compliance -- Privacy and Ethics in the Case of Replika AI [1.325665193924634]
  This paper takes a critical approach towards examining the intricacies of these issues within AI companion services. We analyze articles from public media about the company and its practices to gain insight into the trustworthiness of information provided in the policy. The results reveal despite privacy notices, data collection practices might harvest personal data without users' full awareness.
  arXiv  Detail & Related papers  (2024-11-07T07:36:19Z)
• PrivacyLens: Evaluating Privacy Norm Awareness of Language Models in Action [54.11479432110771]
  PrivacyLens is a novel framework designed to extend privacy-sensitive seeds into expressive vignettes and further into agent trajectories.<n>We instantiate PrivacyLens with a collection of privacy norms grounded in privacy literature and crowdsourced seeds.<n>State-of-the-art LMs, like GPT-4 and Llama-3-70B, leak sensitive information in 25.68% and 38.69% of cases, even when prompted with privacy-enhancing instructions.
  arXiv  Detail & Related papers  (2024-08-29T17:58:38Z)
• Privacy Checklist: Privacy Violation Detection Grounding on Contextual Integrity Theory [43.12744258781724]
  We formulate the privacy issue as a reasoning problem rather than simple pattern matching.<n>We develop the first comprehensive checklist that covers social identities, private attributes, and existing privacy regulations.
  arXiv  Detail & Related papers  (2024-08-19T14:48:04Z)
• Privacy and Copyright Protection in Generative AI: A Lifecycle Perspective [28.968233485060654]
  We discuss the multifaceted challenges of privacy and copyright protection within the data lifecycle. We advocate for integrated approaches that combines technical innovation with ethical foresight. This work aims to catalyze a broader discussion and inspire concerted efforts towards data privacy and copyright integrity in Generative AI.
  arXiv  Detail & Related papers  (2023-11-30T05:03:08Z)
• Can LLMs Keep a Secret? Testing Privacy Implications of Language Models via Contextual Integrity Theory [82.7042006247124]
  We show that even the most capable AI models reveal private information in contexts that humans would not, 39% and 57% of the time, respectively. Our work underscores the immediate need to explore novel inference-time privacy-preserving approaches, based on reasoning and theory of mind.
  arXiv  Detail & Related papers  (2023-10-27T04:15:30Z)
• A Critical Take on Privacy in a Datafied Society [0.0]
  I analyze several facets of the lack of online privacy and idiosyncrasies exhibited by privacy advocates. I discuss of possible effects of datafication on human behavior, the prevalent market-oriented assumption at the base of online privacy, and some emerging adaptation strategies. A glimpse on the likely problematic future is provided with a discussion on privacy related aspects of EU, UK, and China's proposed generative AI policies.
  arXiv  Detail & Related papers  (2023-08-03T11:45:18Z)
• A Randomized Approach for Tight Privacy Accounting [63.67296945525791]
  We propose a new differential privacy paradigm called estimate-verify-release (EVR) EVR paradigm first estimates the privacy parameter of a mechanism, then verifies whether it meets this guarantee, and finally releases the query output. Our empirical evaluation shows the newly proposed EVR paradigm improves the utility-privacy tradeoff for privacy-preserving machine learning.
  arXiv  Detail & Related papers  (2023-04-17T00:38:01Z)
• How Do Input Attributes Impact the Privacy Loss in Differential Privacy? [55.492422758737575]
  We study the connection between the per-subject norm in DP neural networks and individual privacy loss. We introduce a novel metric termed the Privacy Loss-Input Susceptibility (PLIS) which allows one to apportion the subject's privacy loss to their input attributes.
  arXiv  Detail & Related papers  (2022-11-18T11:39:03Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.