← Search

Momin Ahmad Khan

2 accepted papers

2026

SABRE-FL: Selective and Accurate Backdoor Rejection for Federated Prompt Learning

ICLR 2026poster

Federated Prompt Learning has emerged as a communication-efficient and privacy-preserving paradigm for adapting large vision-language models like CLIP across decentralized clients. However, the security implications of this setup remain underexplored. In this work, we present the first study of back…

Cited by 0Source ↗Scholar ↗
2024

HYDRA-FL: Hybrid Knowledge Distillation for Robust and Accurate Federated Learning

NeurIPS 2024poster

Data heterogeneity among Federated Learning (FL) users poses a significant challenge, resulting in reduced global model performance. The community has designed various techniques to tackle this issue, among which Knowledge Distillation (KD)-based techniques are common. While these techniques eff…

Cited by 0Source ↗PDF ↗Scholar ↗