research
∙
05/26/2022
PerDoor: Persistent Non-Uniform Backdoors in Federated Learning using Adversarial Perturbations
Federated Learning (FL) enables numerous participants to train deep lear...
share
research
∙
04/12/2022
Scalable privacy-preserving cancer type prediction with homomorphic encryption
Machine Learning (ML) alleviates the challenges of high-dimensional data...
research
∙
03/17/2022
PiDAn: A Coherence Optimization Approach for Backdoor Attack Detection and Mitigation in Deep Neural Networks
Backdoor attacks impose a new threat in Deep Neural Networks (DNNs), whe...
research
∙
08/14/2021
TRAPDOOR: Repurposing backdoors to detect dataset bias in machine learning-based genomic analysis
Machine Learning (ML) has achieved unprecedented performance in several ...
research
∙
12/30/2020
Explainability Matters: Backdoor Attacks on Medical Imaging
Deep neural networks have been shown to be vulnerable to backdoor attack...
research
∙
06/20/2020
FaceHack: Triggering backdoored facial recognition systems using facial characteristics
Recent advances in Machine Learning (ML) have opened up new avenues for ...
research
∙
03/17/2020