The model compression techniques enable deploying compressed large language models (CMs) at network edge, facilitating convenient provision of AI-generated content (AIGC) services. To ensure timely delivery of these services, efficient placement of CMs across resource-constrained edge networks is essential. In this work, we investigate how to obtain latency-efficient CM placement across resource-constrained edge networks. With the objective of service latency optimization, we formulate the CM placement in resource-constrained network (CPRN) problem and establish its NP-hardness. We propose the Migration-agent-based Deep Reinforcement Learning (M-DRL) approach, which incorporates a specially designed migration agent tailored for such placement problems. To enhance training efficiency, we incorporate efficient heuristic placement results into the environment of M-DRL, developing our Heuristic-guided M-DRL (HM-DRL) approach. Our extensive simulation results demonstrate that HM-DRL outperforms an extended benchmark in service latency, while maintaining a low training overhead.

As on-device large language model (LLM) systems become increasingly prevalent, federated fine-tuning enables advanced language understanding and generation directly on edge devices; however, it also involves processing sensitive, user-specific data, raising significant privacy concerns within the federated learning framework. To address these challenges, we propose DP-FedLoRA, a privacy-enhanced federated fine-tuning framework that integrates LoRA-based adaptation with differential privacy in a communication-efficient setting. Each client locally clips and perturbs its LoRA matrices using Gaussian noise to satisfy (∊, δ)-differential privacy. We further provide a theoretical analysis demonstrating the unbiased nature of the updates and deriving bounds on the variance introduced by noise, offering practical guidance for privacy-budget calibration. Experimental results across mainstream benchmarks show that DP-FedLoRA delivers competitive performance while offering strong privacy guarantees, paving the way for scalable and privacy-preserving LLM deployment in on-device environments.

Assessing data quality in multivariate time-series datasets is crucial for reliable analysis, particularly when dealing with missing values, inconsistent feature availability, and massive records in large-scale edge computing and IoT clusters. Existing methods often fall short of capturing intricate patterns of missingness and co-coverage, restricting the capacity to make well-informed decisions regarding the usability of the data. In order to systematically extract reliable data segments, this paper presents a comprehensive framework that combines a heuristic model with temporal coverage, period-specific missingness, and co-coverage metrics. By integrating these metrics with visualizations such as temporal coverage heatmaps and parallel coordinates plots, the framework reveals complex patterns of missingness while supporting human involvement in validating data subsets. Our approach effectively balances automation with expert judgment, enhancing the interpretability of data quality assessments. The findings show that the proposed methods satisfy the design specifications for revealing patterns, quantifying missingness impact, measuring feature availability, guiding feature selection, and facilitating scalable, multi-scale data summarization. The framework offers a solid way to improve the quality of data in multivariate time-series analysis, opening the door to more precise and trustworthy insights for assessing data gathered from edge computing infrastructures and large-scale, heterogeneous IoT deployments, where data consistency and completeness are frequently very variable.

Recent advances in large language models (LLMs) have empowered robots and drones with autonomous decision-making capabilities. Due to the stringent real-time requirements of these applications, LLM inference must be performed at the network edge. However, hosting high-precision LLMs on a single edge server is often infeasible, creating challenges in efficiently distributing LLM deployments across edge networks. This work addresses these challenges by formulating and solving the profit maximization problem for distributed LLM inference deployment. We first formally define the Profit-Centric Inference Chain Deployment (PC-InCD) problem. To solve PC-InCD, we introduce a novel Local Maximal Profit (LMP) factor that enables effective edge server selection for hosting LLM sub-modules, and we propose the LMP-based Inference Chain Deployment (LMP-InCD) algorithm. Extensive simulations demonstrate that LMP-InCD significantly outperforms benchmark methods in maximizing profit across diverse network conditions.

The integration of Large Language Models (LLMs) into financial technology (FinTech) has revolutionized the analysis and processing of complex financial data, driving advancements in real-time decision-making and analytics. With the growing trend of deploying AI models on edge devices for financial applications, ensuring the privacy of sensitive financial data has become a significant challenge. To address this, we propose DPFinLLM, a privacy-enhanced, lightweight LLM specifically designed for on-device financial applications. DPFinLLM combines a robust differential privacy mechanism with a streamlined architecture inspired by state-of-the-art models, enabling secure and efficient processing of financial data. This proposed DPFinLLM can not only safeguard user data from privacy breaches but also ensure high performance across diverse financial tasks. Extensive experiments on multiple financial sentiment datasets validate the effectiveness of DPFinLLM, demonstrating its ability to achieve performance comparable to fully fine-tuned models, even under strict privacy constraints.

The increasing adoption of Electric Vehicles (EVs) is driving the need for secure, efficient, and intelligent charging systems. While EVs offer a sustainable alternative to conventional vehicles, challenges such as charging station availability, range anxiety, and the privacy risks associated with sharing sensitive data—like location and energy usage—remain significant barriers to broader adoption. To address these challenges, this paper introduces a novel privacy-preserving multi-source data-driven framework for intelligent EV charging optimization. The proposed system combines a hybrid optimization strategy incorporating an enhanced Hungarian Matching Algorithm for cost-efficient EV-to-charging station assignment, a Random Forest regression model for accurate EV range prediction using contextual data, and a Laplace mechanism-based differential privacy module to protect user location data. This unified framework not only improves charging efficiency and predictive accuracy but also provides formal privacy guarantees against inference attacks. Extensive experiments conducted on synthetic datasets demonstrate the framework’s effectiveness in reducing charging costs, enhancing range prediction accuracy, and preserving EV user privacy. The results suggest strong potential for real-world deployment in future intelligent transportation systems.

Multimodal sentiment analysis plays a critical role in numerous IoT-driven applications, such as personalized smart assistants, healthcare monitoring systems, and intelligent transportation networks, where accurate interpretation of user emotions is vital for enhancing service quality. However, a severe threat of privacy leakage in the multimodal sentiment analysis has been overlooked by previous works. To fill this gap, we propose a Differentially Private Correlated Representation Learning (DPCRL) model to achieve privacy-preserving multimodal sentiment analysis by combining a correlated representation learning scheme with a differential privacy protection scheme. Our correlated representation learning scheme aims to achieve heterogeneous multimodal data transformation to meet the requirements of privacy-preserving multimodal sentiment analysis by learning the correlated and uncorrelated representations, where especially, a pre-determined correlation factor is employed to flexibly adjust the expected correlation among the correlated representations. The differential privacy protection scheme is used to obtain the disturbed correlated and uncorrelated representations by adding Laplace noise for -differential privacy. In particular, the correlation factor can help alleviate the side-effect of the added Laplace noise on the sentiment prediction performance. Finally, via conducting a series of real-data experiments, we validate that our proposed DPCRL model is superior to the state of the art for privacy-preserving multimodal sentiment analysis.

In the emerging applications of edge computing (e.g., unmanned factories and meta-verse), network requests are required to be securely and reliably delivered in the form of service function chains (SFCs). To enhance security, security-aware SFs are employed in the SFC, and this type of SFC is referred to as the security-aware SFC (S-SFC). For reliability, service providers can employ a dedicated backup SFC to protect the primary one. However, no existing works addressed the SFC deployment mechanisms that jointly consider SFC reliability and security. For this, here, we investigate the problem of jointly embedding and protecting a security-aware SFC. To efficiently compose, embed, and protect an S-SFC, we propose the S-SFC asymmetric protection concept, which allows the primary and backup SFCs not necessarily to follow an identical structure as the traditional SFC dedicated protection does. Next, we formulate the problem of S-SFC composing, embedding, and protection (S-SFCEP) and prove its NP-hardness. To tackle this problem, we formulate an efficient algorithm, namely, sub-chain-based S-SFC deployment (SCB-SD). Our extensive simulation results show that the proposed SCB-SD outperforms the state-of-the-art benchmarks by an average of 13.86% and 23.19%, respectively.

When multimodal AI systems increasingly utilize diverse data sources to achieve advanced understanding and interaction, they inevitably collect vast amounts of sensitive information, thus highlighting the urgent need for robust privacy safeguards, especially as these technologies expand into fields like healthcare, finance, and education. Existing research on data privacy in AI, encompassing adversarial training-based models, differential privacy-based models, and differentially private transform-based models, often neglects the inter-correlation inherent in multi-sensor data. To address this gap, we propose the differentiAl Private OnLine muLti-sensor data predictiOn model (APOLLO), which simultaneously considers intra-correlation and inter-correlation to enhance privacy protection while maintaining predictive performance. Under the proposed APOLLO frame-work, we design two implementations: APOLLO I, which ensures$\epsilon$-differential privacy by adding Laplace noise to each correlated data segment, and APOLLO II, which applies additional noise to make the concatenated multi-sensor data realize$\epsilon{-}$differential privacy. Furthermore, we conduct the theoretical analysis to reveal the relationship between performance influence and the privacy budget, providing guidelines for noise addition with the aim of achieving certified performance. Comprehensive experiments validate the effectiveness of the APOLLO model, establishing a new standard for privacy-preserving multi-sensor data prediction.

Spiking Neural Networks (SNNs) have recently gained significant interest in on-chip learning in embedded devices and emerged as an energy-efficient alternative to conventional Artificial Neural Networks (ANNs). However, to extend SNNs to a Federated Learning (FL) setting involving collaborative model training, the communication between the local devices and the remote server remains the bottleneck, which is often restricted and costly. In this paper, we first explore the inherent robustness of SNNs under noisy communication in FL. Building upon this foundation, we propose a novel Federated Learning with Top-κ Sparsification (FLTS) algorithm to reduce the bandwidth usage for FL training. We discover that the proposed scheme with SNNs allows more bandwidth savings compared to ANNs without impacting the model’s accuracy. Additionally, the number of parameters to be communicated can be reduced to as low as 6% of the size of the original model. We further improve the communication efficiency by enabling dynamic parameter compression during model training. Extensive experiment results demonstrate that our proposed algorithms significantly outperform the baselines in terms of communication cost and model accuracy and are promising for practical network-efficient FL with SNNs.

Abstract Deep learning‐based models have become ubiquitous across a wide range of applications, including computer vision, natural language processing, and robotics. Despite their efficacy, one of the significant challenges associated with deep neural network (DNN) models is the potential risk of copyright leakage due to the inherent vulnerability of the entire model architecture and the communication burden of the large models during publishing. So far, it is still challenging for us to safeguard the intellectual property rights of these DNN models while reducing the communication time during model publishing. To this end, this paper introduces a novel approach using knowledge distillation techniques aimed at training a surrogate model to stand in for the original DNN model. To be specific, a knowledge distillation generative adversarial network (KDGAN) model is proposed to train a student model capable of achieving remarkable performance levels while simultaneously safeguarding the copyright integrity of the original large teacher model and improving communication efficiency during model publishing. Herein, comprehensive experiments are conducted to showcase the efficacy of model copyright protection, communication‐efficient model publishing, and the superiority of the proposed KDGAN model over other copyright protection mechanisms.

Frequent cyber-attacks force the service provider to employ security-aware service functions (SFs) to accommodate client network requests. Thanks to virtualization techniques' maturity, a security-aware SF can be provided by diverse vendors with various configurations, each of which needs various implementation cost and provides different security levels. When a client's network request comes, the multi-configuration SFs could compose various security-aware service function chains (S-SFCs) to flexibly satisfy the security requirement. In this paper, we investigate how to efficiently compose and embed an S-SFC to satisfy the client's security requirement. With the objective of cost optimization, we formulate the problem of security-aware service function chain deployment and prove its NP-hardness. We propose the technique of the security-cost-balance (SCB) factor to efficiently consider the capability of a physical node and the cost when the node is employed to satisfy the client's security requirement. Based on this technique, we develop an efficient algorithm called SCB-based S-SFC deployment (SCB-SD). The simulation results show that SCB-SD significantly outperforms the benchmarks directly extended from the state-of-the-art.

3D grey image segmentation has become a promising approach to facilitate practical applications with the help of advanced deep learning models. Although a number of previous works have investigated the vulnerability of deep learning models to backdoor attack, there is no work to study the severe risk of backdoor attack on 3D grey image segmentation. To this end, we propose two backdoor attack methods on 3D grey image segmentation, including Full-control Backdoor Attack (FCBA) and Partial-control Backdoor Attack (PCBA), on 3D grey image segmentation by leveraging a frequency trigger injection function and a rotation-based label corruption function. Our proposed trigger injection function is applied to insert a 3D trigger pattern into the benign 3D grey images in the frequency domain while ensuring the invisibility of the trigger pattern. And the proposed rotation-based label corruption function is employed to yield the crafted labels with the aim of decreasing the performance of segmentation. Finally, through comprehensive experiments on a real-world dataset, we demonstrate the effectiveness of our proposed backdoor models, the frequency trigger injection function, and the rotation-based label corruption function.

The demand of sharing video streaming extremely increases due to the proliferation of Internet of Things (IoT) devices in recent years, and the explosive development of artificial intelligent (AI) detection techniques has made visual privacy protection more urgent and difficult than ever before. Although a number of approaches have been proposed, their essential drawbacks limit the effect of visual privacy protection in real applications. In this article, we propose a cycle vector-quantized variational autoencoder (cycle-VQ-VAE) framework to encode and decode the video with its extracted audio, which takes the advantage of multiple heterogeneous data sources in the video itself to protect individuals’ privacy. In our cycle-VQ-VAE framework, a fusion mechanism is designed to integrate the video and its extracted audio. Particularly, the extracted audio works as the random noise with a nonpatterned distribution, which outperforms the noise that follows a patterned distribution for hiding visual information in the video. Under this framework, we design two models, including the frame-to-frame (F2F) model and video-to-video (V2V) model, to obtain privacy-preserving video streaming. In F2F, the video is processed as a sequence of frames; while, in V2V, the relations between frames are utilized to deal with the video, greatly improving the performance of privacy protection, video compression, and video reconstruction. Moreover, the video streaming is compressed in our encoding process, which can resist side-channel inference attack during video transmission and reduce video transmission time. Through the real-data experiments, we validate the superiority of our models (F2F and V2V) over the existing methods in visual privacy protection, visual quality preservation, and video transmission efficiency. The codes of our model implementation and more experimental results are now available athttps://github.com/ahahnut/cycle-VQ-VAE.

Advances in communication technologies and artificial intelligence are accelerating the paradigm of industrial Internet of Things (IIoT). With IIoT enabling continuous integration of sensors and controllers with the network, intelligent analysis of the generated Big Data is a critical requirement. Although IIoT is considered a subset of IoT, it has its own peculiarities in terms of higher levels of safety, security, and low-latency communication in an environment of critical real-time operations. Under these circumstances, discriminative deep learning (DL) algorithms are unsuitable due to their need for large amounts of labeled and balanced training data, uncertainty of inputs, etc. To overcome these issues, researchers have started using deep generative models (DGMs), which combine the flexibility of DL with the inference power of probabilistic modeling. In this article, we review the state of the art of DGMs and their applicability to IIoT, classifying the reviewed works into the IIoT application areas of anomaly detection, trust-boundary protection, network traffic prediction, and platform monitoring. Following an analysis of existing IIoT DGM implementations, we identify challenges (i.e., weak discriminative capability, insufficient interpretability, lack of generalization ability, generated data vulnerability, privacy concern, and data complexity) that need to be investigated in order to accelerate the adoption of DGMs in IIoT and also propose some potential research directions.

Vehicle counting is a fundamental component in Intelligent Transportation System (ITS) for city traffic management. Although a number of vehicle counting approaches have been proposed, their essential drawbacks limit the efficacy of vehicle counting in real applications. In this paper, we propose a CityCam-to-Edge cooperative learning framework by cooperating multiple city cameras with an edge server to count vehicles more efficiently. Our learning framework consists of a lightweight feature extraction scheme deployed on the city cameras and a vehicle counting model implemented on the edge server. We devise the lightweight feature extraction scheme by leveraging multiple convolutional layers with few kernels in the design of deep learning architecture to reduce the utilization of parameters for feature extraction, so that the city cameras’ memory consumption and the data transmission time can be greatly reduced. Moreover, we design two novel vehicle counting models, F2F-M and O2O-M, to improve the counting performance by exploiting the temporal correlation among videos captured from multiple city cameras in a frame-to-frame manner and a video-to-video manner, respectively. By combining the lightweight feature extraction scheme and the proposed vehicle counting models, we obtain two end-to-end vehicle counting models, Lite-F2F-M and Lite-O2O-M. Finally, via conducting extensive experiments, we demonstrate that Lite-F2F-M and Lite-O2O-M models outperform the state-of-the-art in terms of vehicle counting accuracy and time efficiency.

Multi-label image recognition has been an indispensable fundamental component for many real computer vision applications. However, a severe threat of privacy leakage in multi-label image recognition has been overlooked by existing studies. To fill this gap, two privacy-preserving models, Privacy-Preserving Multi-label Graph Convolutional Networks (P2-ML-GCN) and Robust P2-ML-GCN (RP2-ML-GCN), are developed in this article, where differential privacy mechanism is implemented on the model’s outputs so as to defend black-box attack and avoid large aggregated noise simultaneously. In particular, a regularization term is exploited in the loss function of RP2-ML-GCN to increase the model prediction accuracy and robustness. After that, a proper differential privacy mechanism is designed with the intention of decreasing the bias of loss function in P2-ML-GCN and increasing prediction accuracy. Besides, we analyze that a bounded global sensitivity can mitigate excessive noise’s side effect and obtain a performance improvement for multi-label image recognition in our models. Theoretical proof shows that our two models can guarantee differential privacy for model’s outputs, weights and input features while preserving model robustness. Finally, comprehensive experiments are conducted to validate the advantages of our proposed models, including the implementation of differential privacy on model’s outputs, the incorporation of regularization term into loss function, and the adoption of bounded global sensitivity for multi-label image recognition.