PRISM: An Integrated Approach to Support User Comprehension of Mobile Apps' Privacy Practices
Bibliographic record
Abstract
Data privacy has recently become a major concern to many internet users.Privacy labels were proposed and enforced by app platforms to make lengthy and complex privacy policies easier to understand.However, they are often criticized for over simplicity and inaccuracy.To mitigate those issues, we propose PRISM, an integrated tool that augments the existing design of privacy labels by tracing data types in various labels to the relevant content in the privacy policy, app reviews, and community-curated privacy assessments.Our preliminary user study provided insight into how those different resources complement each other.We evaluated the final design of PRISM in a controlled user study.Results indicated that PRISM improves both the efficiency and confidence of mobile users when reasoning about the app's privacy practices.Our work highlights the importance of consolidating and mediating efforts from different parties to support users in better understanding the privacy practices of apps and services.i I want to thank Prof. Guo, Prof. Cheng from Polytechnique Montréal, Prof. Robillard, and my labmates at the Software Technology Lab for fostering a growth-oriented environment that greatly influenced my research.A huge shoutout to Keyu, and Varun, who provided lots of help and ideas to my research and beyond.I thank Mathieu, Deeksha, Lynh, and Bhagya for providing valuable feedback on my tool
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.029 | 0.091 |
| Meta-epidemiology (narrow) | 0.003 | 0.002 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.003 | 0.001 |
| Science and technology studies | 0.001 | 0.002 |
| Scholarly communication | 0.005 | 0.013 |
| Open science | 0.004 | 0.013 |
| Research integrity | 0.003 | 0.004 |
| Insufficient payload (model declined to judge) | 0.011 | 0.004 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".