Harrison Rosenberg
YOU?
Author Swipe
View article: Synthetic Counterfactual Faces
Synthetic Counterfactual Faces Open
Computer vision systems have been deployed in various applications involving biometrics like human faces. These systems can identify social media users, search for missing persons, and verify identity of individuals. While computer vision …
View article: Limitations of Face Image Generation
Limitations of Face Image Generation Open
Text-to-image diffusion models have achieved widespread popularity due to their unprecedented image generation capability. In particular, their ability to synthesize and modify human faces has spurred research into using generated face ima…
View article: Limitations of Face Image Generation
Limitations of Face Image Generation Open
Text-to-image diffusion models have achieved widespread popularity due to their unprecedented image generation capability. In particular, their ability to synthesize and modify human faces has spurred research into using generated face ima…
View article: An Exploration of Multicalibration Uniform Convergence Bounds
An Exploration of Multicalibration Uniform Convergence Bounds Open
Recent works have investigated the sample complexity necessary for fair machine learning. The most advanced of such sample complexity bounds are developed by analyzing multicalibration uniform convergence for a given predictor class. We pr…
View article: Fairness Properties of Face Recognition and Obfuscation Systems
Fairness Properties of Face Recognition and Obfuscation Systems Open
The proliferation of automated face recognition in the commercial and government sectors has caused significant privacy concerns for individuals. One approach to address these privacy concerns is to employ evasion attacks against the metri…
View article: Analyzing Accuracy Loss in Randomized Smoothing Defenses
Analyzing Accuracy Loss in Randomized Smoothing Defenses Open
Recent advances in machine learning (ML) algorithms, especially deep neural networks (DNNs), have demonstrated remarkable success (sometimes exceeding human-level performance) on several tasks, including face and speech recognition. Howeve…
View article: A Geometric Perspective on the Transferability of Adversarial Directions
A Geometric Perspective on the Transferability of Adversarial Directions Open
State-of-the-art machine learning models frequently misclassify inputs that have been perturbed in an adversarial manner. Adversarial perturbations generated for a given input and a specific classifier often seem to be effective on other i…