Search Results for author:
Found 9 papers, 3 papers with code
Universal Debiased Editing on Foundation Models for Fair Medical Image Classification
UDE is capable of mitigating bias both within the FM API embedding and the images themselves.
Backdoor Attack on Unpaired Medical Image-Text Foundation Models: A Pilot Study on MedCLIP
Notably, MedCLIP, a vision-language contrastive learning-based medical FM, has been designed using unpaired image-text training.
Forgettable Federated Linear Learning with Certified Data Removal
To this end, we propose the Forgettable Federated Linear Learning (2F2L) framework featured with novel training and data removal strategies.
Federated Virtual Learning on Heterogeneous Data with Local-global Distillation
To address this, we propose a new method, called Federated Virtual Learning on Heterogeneous Data with Local-Global Distillation (FedLGD), which trains FL using a smaller synthetic dataset (referred as virtual data) created through a combination of local and global dataset distillation.
Backdoor Attack and Defense in Federated Generative Adversarial Network-based Medical Image Synthesis
However, given that the FL server cannot access the raw data, it is vulnerable to backdoor attacks, an adversarial by poisoning training data.
Backdoor Attack is a Devil in Federated GAN-based Medical Image Synthesis
In this study, we propose a way of attacking federated GAN (FedGAN) by treating the discriminator with a commonly used data poisoning strategy in backdoor attack classification models.
On the Convergence of mSGD and AdaGrad for Stochastic Optimization
First, we prove that the iterates of mSGD are asymptotically convergent to a connected set of stationary points with probability one, which is more general than existing works on subsequence convergence or convergence of time averages.
Fast Density Estimation for Density-based Clustering Methods
Density-based clustering algorithms are widely used for discovering clusters in pattern recognition and machine learning since they can deal with non-hyperspherical clusters and are robustness to handle outliers.
PURE: Passive mUlti-peRson idEntification via Deep Footstep Separation and Recognition
Recently, \textit{passive behavioral biometrics} (e. g., gesture or footstep) have become promising complements to conventional user identification methods (e. g., face or fingerprint) under special situations, yet existing sensing technologies require lengthy measurement traces and cannot identify multiple users at the same time.
