87 citations · 96 across the 8 of their papers we have counts for
8 papers
PACOL: Poisoning Attacks Against Continual Learners
Huayu Li, Gregory Ditzler
Continual learning algorithms are typically exposed to untrusted sources that contain training data inserted by adversaries and bad actors. An adversary can insert a small number o…
Knowledge Distillation Under Ideal Joint Classifier Assumption
Huayu Li, Xiwen Chen, Gregory Ditzler +2
Knowledge distillation constitutes a potent methodology for condensing substantial neural networks into more compact and efficient counterparts. Within this context, softmax regres…
A Maximum Log-Likelihood Method for Imbalanced Few-Shot Learning Tasks
Samuel Hess, Gregory Ditzler
Few-shot learning is a rapidly evolving area of research in machine learning where the goal is to classify unlabeled data with only one or "a few" labeled exemplary samples. Neural…
Shadows Aren't So Dangerous After All: A Fast and Robust Defense Against Shadow-Based Adversarial Attacks
Andrew Wang, Wyatt Mayor, Ryan Smith +2
Robust classification is essential in tasks like autonomous vehicle sign recognition, where the downsides of misclassification can be grave. Adversarial attacks threaten the robust…
DeScoD-ECG: Deep Score-Based Diffusion Model for ECG Baseline Wander and Noise Removal
Huayu Li, Gregory Ditzler, Janet Roveda +1
Objective: Electrocardiogram (ECG) signals commonly suffer noise interference, such as baseline wander. High-quality and high-fidelity reconstruction of the ECG signals is of great…
ProtoShotXAI: Using Prototypical Few-Shot Architecture for Explainable AI
Samuel Hess, Gregory Ditzler
Unexplainable black-box models create scenarios where anomalies cause deleterious responses, thus creating unacceptable risks. These risks have motivated the field of eXplainable A…
Adversarial Filters for Secure Modulation Classification
Alex Berian, Kory Staab, Noel Teku +3
Modulation Classification (MC) refers to the problem of classifying the modulation class of a wireless signal. In the wireless communications pipeline, MC is the first operation pe…
Edge-Guided Occlusion Fading Reduction for a Light-Weighted Self-Supervised Monocular Depth Estimation
Kuo-Shiuan Peng, Gregory Ditzler, Jerzy Rozenblit
Self-supervised monocular depth estimation methods generally suffer the occlusion fading issue due to the lack of supervision by the per pixel ground truth. Although a post-process…