Search Results for author:
Found 7 papers, 4 papers with code
A View From Somewhere: Human-Centric Face Representations
Few datasets contain self-identified sensitive attributes, inferring attributes risks introducing additional biases, and collecting attributes can carry legal risks.
Ethical Considerations for Responsible Data Curation
Human-centric computer vision (HCCV) data curation practices often neglect privacy and bias concerns, leading to dataset retractions and unfair models.
Men Also Do Laundry: Multi-Attribute Bias Amplification
We show models can learn to exploit correlations with respect to multiple attributes (e. g., {$\texttt{computer}$, $\texttt{keyboard}$}), which are not accounted for by current metrics.
I call BS: Fraud Detection in Crowdfunding Campaigns
Donations to charity-based crowdfunding environments have been on the rise in the last few years.
Conditional Adversarial Camera Model Anonymization
Model anonymization is the process of transforming these artifacts such that the apparent capture model is changed.
Multiple-Identity Image Attacks Against Face-based Identity Verification
New quantitative results are presented that support an explanation in terms of the geometry of the representations spaces used by the verification systems.
Built-in Vulnerabilities to Imperceptible Adversarial Perturbations
Designing models that are robust to small adversarial perturbations of their inputs has proven remarkably difficult.
