R.I.P.
👻
Ghosted
The Accuracy of the Demographic Inferences Shown on Google's Ad Settings
August 22, 2018 · Declared Dead · 🏛 WPES@CCS
"No code URL or promise found in abstract"
Evidence collected by the PWNC Scanner
Authors
Michael Carl Tschantz, Serge Egelman, Jaeyoung Choi, Nicholas Weaver, Gerald Friedland
arXiv ID
1808.07549
Category
cs.CR: Cryptography & Security
Citations
25
Venue
WPES@CCS
Last Checked
3 months ago
Abstract
Google's Ad Settings shows the gender and age that Google has inferred about a web user. We compare the inferred values to the self-reported values of 501 survey participants. We find that Google often does not show an inference, but when it does, it is typically correct. We explore which usage characteristics, such as using privacy enhancing technologies, are associated with Google's accuracy, but found no significant results.
Community Contributions
Found the code? Know the venue? Think something is wrong? Let us know!
📜 Similar Papers
In the same crypt — Cryptography & Security
R.I.P.
👻
Ghosted
Membership Inference Attacks against Machine Learning Models
R.I.P.
👻
Ghosted
The Limitations of Deep Learning in Adversarial Settings
R.I.P.
👻
Ghosted
Practical Black-Box Attacks against Machine Learning
R.I.P.
👻
Ghosted
Distillation as a Defense to Adversarial Perturbations against Deep Neural Networks
R.I.P.
👻
Ghosted
Extracting Training Data from Large Language Models
Died the same way — 👻 Ghosted
R.I.P.
👻
Ghosted
Language Models are Few-Shot Learners
R.I.P.
👻
Ghosted
PyTorch: An Imperative Style, High-Performance Deep Learning Library
R.I.P.
👻
Ghosted
XGBoost: A Scalable Tree Boosting System
R.I.P.
👻
Ghosted