Zhaomin Wu

Prominent Large Language Model (LLM) services from providers like OpenAI and Google excel at general tasks but often underperform on domain-specific applications. Current customization services for these LLMs typically require users to upload data for fine-tuning, posing significant privacy risks. While differentially private (DP) data synthesis presents a potential alternative, its application commonly results in low effectiveness due to the introduction of excessive noise on data for DP. To overcome this, we introduce Llamdex, a novel framework that facilitates LLM customization as a service, where the client uploads pre-trained domain-specific models rather than data. This client-uploaded model, optionally protected by DP with much lower noise, is inserted into the base LLM via connection modules. Significantly, these connecting modules are trained without requiring sensitive domain data, enabling clients to customize LLM services while preserving data privacy. Experiments demonstrate that Llamdex improves domain-specific accuracy by up to 26% over state-of-the-art private data synthesis methods under identical privacy constraints and, by obviating the need for users to provide domain context within queries, maintains inference efficiency comparable to the original LLM service.

Federated Learning (FL) is an evolving paradigm that enables multiple parties to collaboratively train models without sharing raw data. Vertical Federated Learning (VFL), which involves multiple parties contributing distinct features of a shared instance group, is prevalent in real-world, cross-organizational collaborations. In such setups, parties are typically linked by fuzzy identifiers, a common scenario in practice termed as \textitmulti-party fuzzy VFL. Existing models generally address either multi-party VFL or fuzzy VFL between two parties. Extending these models to the practical multi-party fuzzy VFL typically results in significant performance degradation and increased costs for maintaining privacy. To overcome these limitations, we introduce the \textitFederated Transformer (FeT), a novel framework designed to support multi-party VFL with fuzzy identifiers. FeT encodes identifiers into data representations and conducts training using a transformer architecture distributed across different parties, incorporating three new techniques to enhance performance. Additionally, we have developed a scalable privacy framework that integrates differential privacy with secure multi-party computation, effectively protecting local representations at manageable costs. Experiments show that the FeT surpasses the performance of baseline models by up to 46 percentage points when scaled to 50 parties. Additionally, FeT outperforms cutting-edge models in two-party fuzzy VFL settings, while offering improved privacy.

Vertical Federated Learning (VFL) is a crucial paradigm for training machine learning models on feature-partitioned, distributed data. However, due to privacy restrictions, few public real-world VFL datasets exist for algorithm evaluation, and these represent a limited array of feature distributions. Existing benchmarks often resort to synthetic datasets, derived from arbitrary feature splits from a global set, which only capture a subset of feature distributions, leading to inadequate algorithm performance assessment. This paper addresses these shortcomings by introducing two key factors affecting VFL performance - feature importance and feature correlation - and proposing associated evaluation metrics and dataset splitting methods. Additionally, we introduce a real VFL dataset to address the deficit in image-image VFL scenarios. Our comprehensive evaluation of cutting-edge VFL algorithms provides valuable insights for future research in the field.

As machine learning (ML) has been widely developed in real-world applications, the privacy of ML models draws an increasing concern. In this paper, we study how to forget specific data records from ML models to preserve the privacy of these data. Although some studies propose efficient unlearning algorithms on random forests and extremely randomized trees, Gradient Boosting Decision Trees (GBDT), which are widely used in practice, have not been explored. The efficient unlearning of GBDT faces two major challenges: 1) the training of each tree is deterministic and non-robust; 2) the training of a tree depends on all the previous trees. To solve the first challenge, we propose a robust GBDT-like ML model DeltaBoost that enables efficient and accurate deletion according to our theoretical analysis. For the second challenge, we design a training algorithm for DeltaBoost that minimizes the dependency among trees. Our experiments on five datasets demonstrate that DeltaBoost can remove data records from the trained model efficiently and effectively. Our unlearning approach achieves up to two orders of magnitude speedup compared to retraining GBDT. Besides, DeltaBoost produces competitive performance to existing decision-tree-based ML models.

Federated learning is a learning paradigm to enable collaborative learning across different parties without revealing raw data. Notably, vertical federated learning (VFL), where parties share the same set of samples but only hold partial features, has a wide range of real-world applications. However, most existing studies in VFL disregard the" record linkage”process. They design algorithms either assuming the data from different parties can be exactly linked or simply linking each record with its most similar neighboring record. These approaches may fail to capture the key features from other less similar records. Moreover, such improper linkage cannot be corrected by training since existing approaches provide no feedback on linkage during training. In this paper, we design a novel coupled training paradigm, FedSim, that integrates one-to-many linkage into the training process. Besides enabling VFL in many real-world applications with fuzzy identifiers, FedSim also achieves better performance in traditional VFL tasks. Moreover, we theoretically analyze the additional privacy risk incurred by sharing similarities. Our experiments on eight datasets with various similarity metrics show that FedSim outperforms other state-of-the-art baselines. The codes of FedSim are available at https://github. com/Xtra-Computing/FedSim.