Representation learning with statistical independence to mitigate bias
Presence of bias (in datasets or tasks) is inarguably one of the most critical challenges in
machine learning applications that has alluded to pivotal debates in recent years. Such …
machine learning applications that has alluded to pivotal debates in recent years. Such …
Analyzing privacy leakage in machine learning via multiple hypothesis testing: A lesson from fano
C Guo, A Sablayrolles… - … Conference on Machine …, 2023 - proceedings.mlr.press
Differential privacy (DP) is by far the most widely accepted framework for mitigating privacy
risks in machine learning. However, exactly how small the privacy parameter $\epsilon …
risks in machine learning. However, exactly how small the privacy parameter $\epsilon …
PECAM: Privacy-enhanced video streaming and analytics via securely-reversible transformation
As Video Streaming and Analytics (VSA) systems become increasingly popular, serious
privacy concerns have risen on exposing too much unnecessary private information to the …
privacy concerns have risen on exposing too much unnecessary private information to the …
Posthoc privacy guarantees for collaborative inference with modified Propose-Test-Release
Cloud-based machine learning inference is an emerging paradigm where users query by
sending their data through a service provider who runs an ML model on that data and …
sending their data through a service provider who runs an ML model on that data and …
Privacy-preserving deep action recognition: An adversarial learning framework and a new dataset
We investigate privacy-preserving, video-based action recognition in deep learning, a
problem with growing importance in smart camera applications. A novel adversarial training …
problem with growing importance in smart camera applications. A novel adversarial training …
Deep fair models for complex data: Graphs labeling and explainable face recognition
The central goal of Algorithmic Fairness is to develop AI-based systems which do not
discriminate subgroups in the population with respect to one or multiple notions of inequity …
discriminate subgroups in the population with respect to one or multiple notions of inequity …
Disco: Dynamic and invariant sensitive channel obfuscation for deep neural networks
Recent deep learning models have shown remarkable performance in image classification.
While these deep learning systems are getting closer to practical deployment, the common …
While these deep learning systems are getting closer to practical deployment, the common …
Parallel successive learning for dynamic distributed model training over heterogeneous wireless networks
Federated learning (FedL) has emerged as a popular technique for distributing model
training over a set of wireless devices, via iterative local updates (at devices) and global …
training over a set of wireless devices, via iterative local updates (at devices) and global …
Bounding the invertibility of privacy-preserving instance encoding using fisher information
Privacy-preserving instance encoding aims to encode raw data into feature vectors without
revealing their privacy-sensitive information. When designed properly, these encodings can …
revealing their privacy-sensitive information. When designed properly, these encodings can …
Balancing biases and preserving privacy on balanced faces in the wild
There are demographic biases present in current facial recognition (FR) models. To
measure these biases across different ethnic and gender subgroups, we introduce our …
measure these biases across different ethnic and gender subgroups, we introduce our …