Efficient attribute unlearning: Towards selective removal of input attributes from feature representations
Recently, the enactment of privacy regulations has promoted the rise of the machine
unlearning paradigm. Existing studies of machine unlearning mainly focus on sample-wise …
unlearning paradigm. Existing studies of machine unlearning mainly focus on sample-wise …
GBDF: gender balanced deepfake dataset towards fair deepfake detection
AV Nadimpalli, A Rattani - International Conference on Pattern …, 2022 - Springer
Facial forgery by deepfakes has raised severe societal concerns. Several solutions have
been proposed by the vision community to effectively combat the misinformation on the …
been proposed by the vision community to effectively combat the misinformation on the …
Fairness in face presentation attack detection
Face recognition (FR) algorithms have been proven to exhibit discriminatory behaviors
against certain demographic and non-demographic groups, raising ethical and legal …
against certain demographic and non-demographic groups, raising ethical and legal …
Robustness disparities in face detection
Facial analysis systems have been deployed by large companies and critiqued by scholars
and activists for the past decade. Many existing algorithmic audits examine the performance …
and activists for the past decade. Many existing algorithmic audits examine the performance …
Learning to split for automatic bias detection
Y Bao, R Barzilay - arXiv preprint arXiv:2204.13749, 2022 - arxiv.org
Classifiers are biased when trained on biased datasets. As a remedy, we propose Learning
to Split (ls), an algorithm for automatic bias detection. Given a dataset with input-label pairs …
to Split (ls), an algorithm for automatic bias detection. Given a dataset with input-label pairs …
A novel approach for bias mitigation of gender classification algorithms using consistency regularization
A Krishnan, A Rattani - Image and Vision Computing, 2023 - Elsevier
Published research has confirmed the bias of automated face-based gender classification
algorithms across gender-racial groups. Specifically, unequal accuracy rates were obtained …
algorithms across gender-racial groups. Specifically, unequal accuracy rates were obtained …
Zero-shot racially balanced dataset generation using an existing biased stylegan2
Facial recognition systems have made significant strides thanks to data-heavy deep learning
models, but these models rely on large privacy-sensitive datasets. Further, many of these …
models, but these models rely on large privacy-sensitive datasets. Further, many of these …
Adventures of Trustworthy Vision-Language Models: A Survey
Recently, transformers have become incredibly popular in computer vision and vision-
language tasks. This notable rise in their usage can be primarily attributed to the capabilities …
language tasks. This notable rise in their usage can be primarily attributed to the capabilities …
On responsible machine learning datasets emphasizing fairness, privacy and regulatory norms with examples in biometrics and healthcare
Artificial Intelligence (AI) has seamlessly integrated into numerous scientific domains,
catalysing unparalleled enhancements across a broad spectrum of tasks; however, its …
catalysing unparalleled enhancements across a broad spectrum of tasks; however, its …