6 papers · 1 filter
MPU: Towards Secure and Privacy-Preserving Knowledge Unlearning for Large Language Models
Tiantong Wang, Xinyu Yan, Tiantong Wu +3
Machine unlearning for large language models often faces a privacy dilemma in which strict constraints prohibit sharing either the server's parameters or the client's forget set. T…
Certified Robustness under Heterogeneous Perturbations via Hybrid Randomized Smoothing
Blaise Delattre, Hengyu Wu, Paul Caillon +2
Randomized smoothing provides strong, model-agnostic robustness certificates, but existing guarantees are limited to single modalities, treating continuous and discrete inputs in i…
M-Loss: Quantifying Model Merging Compatibility with Limited Unlabeled Data
Tiantong Wang, Yiyang Duan, Haoyu Chen +2
Training of large-scale models is both computationally intensive and often constrained by the availability of labeled data. Model merging offers a compelling alternative by directl…
Oblivionis: A Lightweight Learning and Unlearning Framework for Federated Large Language Models
Fuyao Zhang, Xinyu Yan, Tiantong Wu +7
Large Language Models (LLMs) increasingly leverage Federated Learning (FL) to utilize private, task-specific datasets for fine-tuning while preserving data privacy. However, while…
Unlearning through Knowledge Overwriting: Reversible Federated Unlearning via Selective Sparse Adapter
Zhengyi Zhong, Weidong Bao, Ji Wang +4
Federated Learning is a promising paradigm for privacy-preserving collaborative model training. In practice, it is essential not only to continuously train the model to acquire new…
Enhancing Federated Domain Adaptation with Multi-Domain Prototype-Based Federated Fine-Tuning
Jingyuan Zhang, Yiyang Duan, Shuaicheng Niu +2
Federated Domain Adaptation (FDA) is a Federated Learning (FL) scenario where models are trained across multiple clients with unique data domains but a shared category space, witho…