Recent advancements in pre-trained large language models (LLMs) have significantly influenced various domains. Adapting these models for specific tasks often involves fine-tuning (FT) with private, domain-specific data. However, privacy concerns keep this data undisclosed, and the computational demands for deploying LLMs pose challenges for resource-limited data holders. This has sparked interest in split learning (SL), a Model-as-a-Service (MaaS) paradigm that divides LLMs into smaller segments for distributed training and deployment, transmitting only intermediate activations instead of raw data. SL has garnered substantial interest in both industry and academia as it aims to balance user data privacy, model ownership, and resource challenges in the private fine-tuning of LLMs. Despite its privacy claims, this paper reveals significant vulnerabilities arising from the combination of SL and LLM-FT: the Not-too-far property of fine-tuning and the auto-regressive nature of LLMs. Exploiting these vulnerabilities, we propose Bidirectional Semi-white-box Reconstruction (BiSR), the first data reconstruction attack (DRA) designed to target both the forward and backward propagation processes of SL. BiSR utilizes pre-trained weights as prior knowledge, combining a learning-based attack with a bidirectional optimization-based approach for highly effective data reconstruction. Additionally, it incorporates a Noise-adaptive Mixture of Experts (NaMoE) model to enhance reconstruction performance under perturbation. We conducted systematic experiments on various mainstream LLMs and different setups, empirically demonstrating BiSR's state-of-the-art performance. Furthermore, we thoroughly examined three representative defense mechanisms, showcasing our method's capability to reconstruct private data even in the presence of these defenses.

A wireless body area network (WBAN) is a crucial technology for implementing intelligent health monitoring. Traditional WBANs focus on the monitoring and classification of single physiological signals, which cannot meet the comprehensive requirements for monitoring human health and behavior. This paper proposes a local feature channel fusion convolutional neural network (CNN) model that can monitor and analyze multiple physiological signals collected by WBANs and can be used for disease identification and human activity recognition. The model employs convolution kernels to perform convolution operations on each channel, extracting local features of each channel and then performing channel fusion convolution operations to effectively integrate information between different channels. Additionally, the model incorporates an attention mechanism to dynamically adjust feature weights, highlight important features, and suppress redundant information. Experiments conducted on 11 WBAN-related datasets from the UEA database demonstrate that the proposed model achieves optimal classification performance.

Abstract We present VRTree, an example‐based interactive virtual reality (VR) system designed to efficiently create diverse 3D tree models while faithfully preserving botanical characteristics of real‐world references. Our method employs a novel representation called Hierarchical Branch Lobe (HBL), which captures the hierarchical features of trees and serves as a versatile intermediary for intuitive VR interaction. The HBL representation decomposes a 3D tree into a series of concise examples, each consisting of a small set of main branches, secondary branches, and lobe‐bounded twigs. The core of our system involves two key components: (1) We design an automatic algorithm to extract an initial library of HBL examples from real tree point clouds. These HBL examples can be optionally refined according to user intentions through an interactive editing process. (2) Users can interact with the extracted HBL examples to assemble new tree structures, ensuring the local features align with the target tree species. A shape‐guided procedural growth algorithm then transforms these assembled HBL structures into highly realistic, finegrained 3D tree models. Extensive experiments and user studies demonstrate that VRTree outperforms current state‐of‐the‐art approaches, offering a highly effective and easy‐to‐use VR tool for tree modeling.

Image alignment and registration methods typically rely on visual correspondences across common regions and boundaries to guide the alignment process. Without them, the problem becomes significantly more challenging. Nevertheless, in real world, image fragments may be corrupted with no common boundaries and little or no overlap. In this work, we address the problem of learning the alignment of image fragments with gaps (i.e., without common boundaries or overlapping regions). Our setting is unsupervised, having only the fragments at hand with no ground truth to guide the alignment process. This is usually the situation in the restoration of unique archaeological artifacts such as frescoes and mosaics. Hence, we suggest a self-supervised approach utilizing self-examples which we generate from the existing data and then feed into an adversarial neural network. Our idea is that available information inside fragments is often sufficiently rich to guide their alignment with good accuracy. Following this observation, our method splits the initial fragments into sub-fragments yielding a set of aligned pieces. Thus, sub-fragmentation allows exposing new alignment relations and revealing inner structures and feature statistics. In fact, the new sub-fragments construct true and false alignment relations between fragments. We feed this data to a spatial transformer GAN which learns to predict the alignment between fragments gaps. We test our technique on various synthetic datasets as well as large scale frescoes and mosaics. Results demonstrate our method's capability to learn the alignment of deteriorated image fragments in a self-supervised manner, by examining inner image statistics for both synthetic and real data.