Search arXiv⌕ Search
Home/Archive/arXiv

arXiv · 2403.05586

From Speech to Data: Unraveling Google's Use of Voice Data for User Profiling

Xinhang Ma·Sirui Chen
View original source ↗Read source document ↗Export metadata ↓

Abstract

Smart home voice assistants enable users to conveniently interact with IoT devices and perform Internet searches; however, they also collect the voice input that can carry sensitive personal information about users. Previous papers investigated how information inferred from the contents of users' voice commands are shared or leaked for tracking and advertising purposes. In this paper, we systematically evaluate how voice itself is used for user profiling in the Google ecosystem. To do so, we simulate various user personas by engaging with specific categories of websites. We then use \textit{neutral voice commands}, which we define as voice commands that neither reveal personal interests nor require Google smart speakers to use the search APIs, to interact with these speakers. We also explore the effects of the non-neutral voice commands for user profiling. Notably, we employ voices that typically would not match the predefined personas. We then iteratively improve our experiments based on observations of profile changes to better simulate real-world user interactions with smart speakers. We find that Google uses these voice recordings for user profiling, and in some cases, up to 5 out of the 8 categories reported by Google for customizing advertisements are altered following the collection of the voice commands.

Explore related subjects

cs.HC

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Xinhang Ma, Sirui Chen. 2024-03-03. From Speech to Data: Unraveling Google's Use of Voice Data for User Profiling. https://arxiv.org/abs/2403.05586

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

ADSEL: Adaptive Dual Self-Expression Learning for EEG Feature Selection via Incomplete Multi-Dimensional Emotion Labels

EEG based multi-dimension emotion recognition has attracted substantial research interest in affective computing. However, the high dimensionality of EEG features, coupled with limited sample sizes, frequently leads to classifier overfitting and high computational complexity. Feature selection constitutes a critical strategy for mitigating these challenges. However, most existing EEG feature selection methods assume complete multi-dimensional emotion labels. In practice, open acquisition environment and the inherent subjectivity of emotion perception often result in incomplete label data, which can compromise model generalization. Additionally, existing feature selection methods for handling incomplete multi-dimensional labels primarily focus on correlations among various dimensions during label recovery, neglecting the correlation between samples in the label space and their interaction with various dimensions. To address these issues, we propose a novel incomplete multi-dimensional emotion feature selection framework integrating Adaptive Dual Self-Expression Learning (ADSEL) with least squares regression. ADSEL could establish a bidirectional pathway between sample-level and dimension-level self-expression learning processes within the label space. It could facilitate the cross-sharing of learned information between these processes, enabling the simultaneous exploitation of effective information across both samples and dimensions for label reconstruction. Consequently, ADSEL could enhance label recovery accuracy and effectively identifies the optimal EEG feature subset for multi-dimensional emotion recognition. ADSEL was evaluated against fourteen state-of-the-art feature selection methods on three public EEG datasets with multi-dimensional emotion labels. Experimental results demonstrate that ADSEL could achieve superior performance under conditions of partial label absence.

cs.HC↗
arXiv2026

A Human-AI Collaborative Workflow for Mathematical Discovery: A Case Study in Grover-Compatible Riemannian Optimization

We investigate how large language models can be used as research tools in scientific computing while preserving mathematical rigor. We propose a human-in-the-loop workflow for interactive theorem proving and discovery with LLMs. Human experts retain control over problem formulation and assumptions, while the model searches for proofs or contradictions, proposes candidate properties and theorems, and helps construct structures and parameters that satisfy explicit constraints, supported by numerical experiments and simple verification checks. Experts treat these outputs as raw material, further refine them, and organize the results into precise statements and rigorous proofs. We instantiate this workflow in a main case study on the connection between manifold optimization and Grover's quantum search algorithm, where the pipeline identifies invariant subspaces and explores Grover-compatible retractions. The main case study uses the corresponding Grover-compatible convergence analysis, including an $O(\sqrt{N} \log(1/\varepsilon))$ PL-based bound established in the companion mathematical work, to illustrate the refinement stage of the workflow. Prompt records and reusable templates for implementing the workflow are provided. We further include a multi-oracle case study, document representative failed and corrected routes arising from this setting, and provide a structured failure-mode analysis.

cs.HC↗
arXiv2026

Learning Password Best Practices Through In-Task Instruction

Users often make security- and privacy-relevant decisions without a clear understanding of the rules that govern safe behavior. We introduce pedagogical friction, a design approach that inserts brief, instructional interactions at the moment of action. We evaluate this approach in the context of password creation, a familiar task with clear quality criteria. We conducted a randomized study with 128 participants across four interface conditions that varied the depth and interactivity of guidance. We assessed three outcomes: (1) rule compliance in a subsequent password task without guidance, (2) accuracy on survey questions tied to password rules, and (3) behavior-knowledge alignment, which captures whether participants who correctly followed a rule also recognized it on the survey. Across the guided conditions, participants corrected most rule violations in the follow-up task and showed high behavior-knowledge alignment. Survey results suggested clearer advantages for some rule types, especially symbol related questions. These results position pedagogical friction as a lightweight intervention for security- and privacy-critical interfaces.

cs.HC↗