collaborators

6 papers

cs.CR2026

Continual Backdoor Training in IoT/CPS

Oxana Salish, Kuniyilh S

Internet of Things (IoT) and Cyber-physical systems (CPS) increasingly rely on continual learning (CL) to adapt to evolving environments, device heterogeneity, and concept drift, t…

cs.CR2026

Backdoor Attacks on Fault Detection and Localization in Cyber-Physical Systems

Abile Jean, Kuniyilh S

Cyber-Physical Systems (CPS) integrate sensing, communication, computation, and control to support critical infrastructure, including smart grids, industrial automation, and contro…

cs.LG2026

CFD-HAR: User-controllable Privacy through Conditional Feature Disentanglement

Alex Gn, Fan Li, S Kuniyilh +1

Modern wearable and mobile devices are equipped with inertial measurement units (IMUs). Human Activity Recognition (HAR) applications running on such devices use machine-learning-b…

cs.LG2026

Backdoor Attacks on Contrastive Continual Learning for IoT Systems

Alfous Tim, Kuniyilh Simi D

The Internet of Things (IoT) systems increasingly depend on continual learning to adapt to non-stationary environments. These environments can include factors such as sensor drift,…

cs.LG2026

Contrastive Learning for Privacy Enhancements in Industrial Internet of Things

Lin Liu, Rita Machacy, Simi Kuniyilh

The Industrial Internet of Things (IIoT) integrates intelligent sensing, communication, and analytics into industrial environments, including manufacturing, energy, and critical in…

cs.LG2026

Backdoor Attacks on Multi-modal Contrastive Learning

Simi D Kuniyilh, Rita Machacy

Contrastive learning has become a leading self- supervised approach to representation learning across domains, including vision, multimodal settings, graphs, and federated learning…