Abstract In Federated Learning (FL), models are as fragile as centrally trained models against adversarial examples. However, the adversarial robustness of federated learning …
D Cai, Y Wu, S Wang, FX Lin, M Xu - Proceedings of the 29th Annual …, 2023 - dl.acm.org
Transformer-based pre-trained models have revolutionized NLP for superior performance and generality. Fine-tuning pre-trained models for downstream tasks often requires private …
D Cai, S Wang, Y Wu, FX Lin, M Xu - Proceedings of the 29th Annual …, 2023 - dl.acm.org
Natural language processing (NLP) sees rich mobile applications. To support various language understanding tasks, a foundation NLP model is often fine-tuned in a federated …
D Cai, Y Wu, S Wang, FX Lin, M Xu - arXiv preprint arXiv:2205.10162, 2022 - arxiv.org
Transformer-based pre-trained models have revolutionized NLP for superior performance and generality. Fine-tuning pre-trained models for downstream tasks often requires private …
Protecting the privacy of user data is crucial for text generation models, which can leak sensitive information during generation. Differentially private (DP) learning methods provide …
Y Song, J Zhang, Z Tian, Y Yang, M Huang… - arXiv preprint arXiv …, 2024 - arxiv.org
As sufficient data are not always publically accessible for model training, researchers exploit limited data with advanced learning algorithms or expand the dataset via data augmentation …
A da Cunha, F d'Amore, F Giroire, H Lesfari… - arXiv preprint arXiv …, 2022 - arxiv.org
The average properties of the well-known Subset Sum Problem can be studied by the means of its randomised version, where we are given a target value $ z $, random variables …
In the Random Subset Sum Problem, given $ n $ iid random variables $ X_1,..., X_n $, we wish to approximate any point $ z\in [-1, 1] $ as the sum of a suitable subset $ X_ {i_1 (z)} …
L Ntantiso, A Bagula, O Ajayi… - … Conference on e …, 2022 - Springer
In today's world, artificial intelligence (AI) and machine learning (ML) are being widely adopted at an exponential rate. A key requirement of AI and ML models is data, which often …