Search Results for author:
Found 6 papers, 1 papers with code
Differentially Private and Adversarially Robust Machine Learning: An Empirical Evaluation
Malicious adversaries can attack machine learning models to infer sensitive information or damage the system by launching a series of evasion attacks.
Elevating Defenses: Bridging Adversarial Training and Watermarking for Model Resilience
We use adversarial training together with adversarial watermarks to train a robust watermarked model.
FedSpectral+: Spectral Clustering using Federated Learning
While the distributed spectral clustering algorithm exists, they face the problem of data privacy and increased communication costs between the clients.
k-Means SubClustering: A Differentially Private Algorithm with Improved Clustering Quality
These DP mechanisms do not guarantee convergence of differentially private iterative algorithms and degrade the quality of the cluster.
Merged-GHCIDR: Geometrical Approach to Reduce Image Data
We propose two variations: Geometrical Homogeneous Clustering for Image Data Reduction (GHCIDR) and Merged-GHCIDR upon the baseline algorithm - Reduction through Homogeneous Clustering (RHC) to achieve better accuracy and training time.
Geometrical Homogeneous Clustering for Image Data Reduction
The intuition behind the first approach, RHCKON, is that the boundary points contribute significantly towards the representation of clusters.
