90 citations · 149 across the 19 of their papers we have counts for
22 papers
Evaluating Trade-offs in Computer Vision Between Attribute Privacy, Fairness and Utility
William Paul, Philip Mathew, Fady Alajaji +1
This paper investigates to what degree and magnitude tradeoffs exist between utility, fairness and attribute privacy in computer vision. Regarding privacy, we look at this importan…
Addressing Heterogeneity in Federated Learning via Distributional Transformation
Haolin Yuan, Bo Hui, Yuchen Yang +3
Federated learning (FL) allows multiple clients to collaboratively train a deep learning model. One major challenge of FL is when data distribution is heterogeneous, i.e., differs…
Classification Utility, Fairness, and Compactness via Tunable Information Bottleneck and Rényi Measures
Adam Gronowski, William Paul, Fady Alajaji +2
Designing machine learning algorithms that are accurate yet fair, not discriminating based on any sensitive attribute, is of paramount importance for society to accept AI for criti…
Renyi Fair Information Bottleneck for Image Classification
Adam Gronowski, William Paul, Fady Alajaji +2
We develop a novel method for ensuring fairness in machine learning which we term as the Renyi Fair Information Bottleneck (RFIB). We consider two different fairness constraints -…
Robustness and Adaptation to Hidden Factors of Variation
William Paul, Philippe Burlina
We tackle here a specific, still not widely addressed aspect, of AI robustness, which consists of seeking invariance / insensitivity of model performance to hidden factors of varia…
EdgeMixup: Improving Fairness for Skin Disease Classification and Segmentation
Haolin Yuan, Armin Hadzic, William Paul +5
Skin lesions can be an early indicator of a wide range of infectious and other diseases. The use of deep learning (DL) models to diagnose skin lesions has great potential in assist…
Patch Attack Invariance: How Sensitive are Patch Attacks to 3D Pose?
Max Lennon, Nathan Drenkow, Philippe Burlina
Perturbation-based attacks, while not physically realizable, have been the main emphasis of adversarial machine learning (ML) research. Patch-based attacks by contrast are physical…
Adaptation and Generalization for Unknown Sensitive Factors of Variations
William Paul, Philippe Burlina
Assured AI in unrestricted settings is a critical problem. Our framework addresses AI assurance challenges lying at the intersection of domain adaptation, fairness, and counterfact…
AI Fairness via Domain Adaptation
Neil Joshi, Phil Burlina
While deep learning (DL) approaches are reaching human-level performance for many tasks, including for diagnostics AI, the focus is now on challenges possibly affecting DL deployme…
Defending Medical Image Diagnostics against Privacy Attacks using Generative Methods
William Paul, Yinzhi Cao, Miaomiao Zhang +1
Machine learning (ML) models used in medical imaging diagnostics can be vulnerable to a variety of privacy attacks, including membership inference attacks, that lead to violations…
Practical Blind Membership Inference Attack via Differential Comparisons
Bo Hui, Yuchen Yang, Haolin Yuan +3
Membership inference (MI) attacks affect user privacy by inferring whether given data samples have been used to train a target learning model, e.g., a deep neural network. There ar…
Addressing Visual Search in Open and Closed Set Settings
Nathan Drenkow, Philippe Burlina, Neil Fendley +2
Searching for small objects in large images is a task that is both challenging for current deep learning systems and important in numerous real-world applications, such as remote s…
Attack Agnostic Detection of Adversarial Examples via Random Subspace Analysis
Nathan Drenkow, Neil Fendley, Philippe Burlina
Whilst adversarial attack detection has received considerable attention, it remains a fundamentally challenging problem from two perspectives. First, while threat models can be wel…
TARA: Training and Representation Alteration for AI Fairness and Domain Generalization
William Paul, Armin Hadzic, Neil Joshi +2
We propose a novel method for enforcing AI fairness with respect to protected or sensitive factors. This method uses a dual strategy performing training and representation alterati…
AI Progress in Skin Lesion Analysis
Philippe M. Burlina, William Paul, Phil A. Mathew +3
We examine progress in the use of AI for detecting skin lesions, with particular emphasis on the erythema migrans rash of acute Lyme disease, and other lesions, such as those from…
Least th-Order and Rényi Generative Adversarial Networks
Himesh Bhatia, William Paul, Fady Alajaji +2
We investigate the use of parametrized families of information-theoretic measures to generalize the loss functions of generative adversarial networks (GANs) with the objective of i…
Jacks of All Trades, Masters Of None: Addressing Distributional Shift and Obtrusiveness via Transparent Patch Attacks
Neil Fendley, Max Lennon, I-Jeng Wang +2
We focus on the development of effective adversarial patch attacks and -- for the first time -- jointly address the antagonistic objectives of attack success and obtrusiveness via…
Addressing Artificial Intelligence Bias in Retinal Disease Diagnostics
Philippe Burlina, Neil Joshi, William Paul +2
This study evaluated generative methods to potentially mitigate AI bias when diagnosing diabetic retinopathy (DR) resulting from training data imbalance, or domain generalization w…
Unsupervised Discovery, Control, and Disentanglement of Semantic Attributes with Applications to Anomaly Detection
William Paul, I-Jeng Wang, Fady Alajaji +1
Our work focuses on unsupervised and generative methods that address the following goals: (a) learning unsupervised generative representations that discover latent factors controll…
Occupancy Map Prediction Using Generative and Fully Convolutional Networks for Vehicle Navigation
Kapil Katyal, Katie Popek, Chris Paxton +4
Fast, collision-free motion through unknown environments remains a challenging problem for robotic systems. In these situations, the robot's ability to reason about its future moti…
Deep Learning based Retinal OCT Segmentation
Mike Pekala, Neil Joshi, David E. Freund +3
Our objective is to evaluate the efficacy of methods that use deep learning (DL) for the automatic fine-grained segmentation of optical coherence tomography (OCT) images of the ret…
Combining Deep Universal Features, Semantic Attributes, and Hierarchical Classification for Zero-Shot Learning
Jared Markowitz, Aurora C. Schmidt, Philippe M. Burlina +1
We address zero-shot (ZS) learning, building upon prior work in hierarchical classification by combining it with approaches based on semantic attribute estimation. For both non-nov…