The distributed (federated) LLM is an important method for co-training the domain-specific LLM using siloed data. However, maliciously stealing model parameters and data from the server or client side has become an urgent problem to be solved. In this paper, we propose a secure distributed LLM based on model slicing. In this case, we deploy the Trusted Execution Environment (TEE) on both the client and server side, and put the fine-tuned structure (LoRA or embedding of P-tuning v2) into the TEE. Then, secure communication is executed in the TEE and general environments through lightweight encryption. In order to further reduce the equipment cost as well as increase the model performance and accuracy, we propose a split fine-tuning scheme. In particular, we split the LLM by layers and place the latter layers in a server-side TEE (the client does not need a TEE). We then combine the proposed Sparsification Parameter Fine-tuning (SPF) with the LoRA part to improve the accuracy of the downstream task. Numerous experiments have shown that our method guarantees accuracy while maintaining security.

With the increasing penetration of renewable energy and flexible loads in smart grids, a more complicated power system with high uncertainty is gradually formed, which brings about great challenges to smart grid operations. Traditional optimization methods usually require accurate mathematical models and parameters and cannot deal well with the growing complexity and uncertainty. Fortunately, the widespread popularity of advanced meters makes it possible for smart grid to collect massive data, which offers opportunities for data-driven artificial intelligence methods to address the optimal operation and control issues. Therein, deep reinforcement learning (DRL) has attracted extensive attention for its excellent performance in operation problems with high uncertainty. To this end, this article presents a comprehensive literature survey on DRL and its applications in smart grid operations. First, a detailed overview of DRL, from fundamental concepts to advanced models, is conducted in this article. Afterward, we review various DRL techniques as well as their extensions developed to cope with emerging issues in the smart grid, including optimal dispatch, operational control, electricity market, and other emerging areas. In addition, an application-oriented survey of DRL in smart grid is presented to identify difficulties for future research. Finally, essential challenges, potential solutions, and future research directions concerning the DRL applications in smart grid are also discussed.

Privacy-preserving machine learning has drawn increasingly attention recently, especially with kinds of privacy regulations come into force. Under such situation, Federated Learning (FL) appears to facilitate privacy-preserving joint modeling among multiple parties. Although many federated algorithms have been extensively studied, there is still a lack of secure and practical gradient tree boosting models (e.g., XGB) in literature. In this paper, we aim to build large-scale secure XGB under vertically federated learning setting. We guarantee data privacy from three aspects. Specifically, (1) we employ secure multi-party computation techniques to avoid leaking intermediate information during training, (2) we store the output model in a distributed manner in order to minimize information release, and (3) we provide a novel algorithm for secure XGB predict with the distributed model. Furthermore, by proposing secure permutation protocols, we can improve the training efficiency and make the framework scale to large dataset. We conduct extensive experiments on both public datasets and real-world datasets, and the results demonstrate that our proposed XGB models provide not only competitive accuracy but also practical performance.