The mobile health (mHealth) system, leveraging mobile edge computing, can monitor health status and provide diagnosis. However, due to the privacy of medical data and the resource limitations of mobile devices, patients are unable to access diagnostic services provided by untrusted servers in real-time. Existing schemes present significant challenges in private heterogeneous data aggregation, model training and inference in the presence of malicious participants, and expensive resource consumption. To address these issues, in this paper, we propose a non-interactive privacy-preserving system with the naive Bayesian model, i.e.,$\mathsf {RobustHealth}$, for heterogeneous mHealth diagnosis. Specifically, we extract homogeneous features from heterogeneous datasets to enable efficient encrypted aggregation. We propose a novel private model training algorithm with enhanced security to against collusion-then-differential attacks. We develop a novel non-interactive private model inference algorithm using minimal lightweight cryptographic primitives, designed for patients under unstable network environments. We provide formal security proofs for our system using the Universal Composable (UC) framework. To validate the performance of$\mathsf {RobustHealth}$, we conduct extensive experiments on real-world heterogeneous datasets, and compared with related works. The results demonstrate a$\bf {4.37\%}$improvement in model accuracy, along with significant reductions in computational and communication overheads of$\bf {21.18\times }$and$\bf {4.24\times }$, respectively.

Split learning, as a distributed learning framework, effectively addresses the issue of limited computing resources. However, despite achieving a separation of data and computation, recent studies have pointed out that this framework still faces two major security challenges: privacy leakage and model security. Most current research focuses on the problem of privacy leakage, emphasizing how to prevent malicious servers from recovering or inferring the client's private data. However, the issue of model security in split learning has not received sufficient attention. This paper reveals the vulnerability of split learning to backdoor attacks. Since split learning cannot access client data directly, it can only guide the client model to incorporate backdoors through gradients. To address this issue, we design an attack framework that modifies intermediate activations to influence the gradients. We designed a parrot model that learns the client’s feature space, enabling the server to obtain the intermediate activations of poisoned data. During the forward pass, some of the intermediate activations and labels transmitted from the client to the server are replaced with poisoned activations and target labels. This replacement method effectively integrates the backdoor task into the model while partially retaining the main task. This approach ensures that the main task is preserved while seamlessly embedding the backdoor task. Our attack framework minimizes reliance on client knowledge and ensures that the attack process remains undetectable by the client. Through extensive experiments, we demonstrated high attack success rates using triggers such as BadNet, SIG, Blended, and WaNet, while minimizing the impact on the main task.

Recent advanced persistent backdoor attacks pose a serious security challenge for federated learning, allowing backdoors to be injected into the global model with lifespans of nearly a thousand rounds after the attack ceases. Existing anomaly detection-based defenses can effectively detect abnormal client models, but are limited in actively eliminating already implanted persistent backdoors. Other defenses such as norm clipping and differential privacy could shorten the lifespan of backdoors, but they would affect model performance. In this work, we propose FLdetox, a multi-layered defensive framework to detoxify persistent backdoors without relying on auxiliary datasets while guaranteeing the desirable performance of the main task. Specifically, FLdetox slows backdoor implantation speed through fine-grained clipping and weight freezing, eliminates already implanted backdoors by retraining stable weights, and hinders attackers from optimizing their attacks through decoy global models. Extensive experimental results validate that, FLdetox effectively prevents and rapidly eliminates the implantation of state-of-the-art persistent backdoors, including Neurotoxin, DBA, F3BA, and A3FL while maintaining high performance of the main task.

SplitFed Learning (SFL) represents a compelling distributed learning paradigm tailored for resource-constrained edge computing scenarios, wherein the privacy threat posed by Gradient Inversion Attacks (GIA) remains challenging. The unique architecture of SFL restricts the fed server’s access only to the client-side model’sdeficient gradients, which lack essential information about the original data. This absence of complete gradient information hinders traditional GIA methods, which rely on complete gradient information for effective data reconstruction, thereby significantly diminishing their effectiveness in the SFL context. In this paper, we propose a novel attack against SFL calledDeficient Gradient-based Inversion Attack(DGIA), which reconstructs original training data by artificially amplifying the ℓ2norm of deficient gradients. Through extensive evaluation of how GIA performance varies with different gradient magnitudes, we observe a definitive correlation between the gradient ℓ2norm and attack performance. Based on this correlation, we further optimize DGIA to identify the optimal gradient amplification scale that maximizes the information encoded in deficient gradients. This compensates for the restricted access to complete gradients and enhances the attack performance. We conduct extensive experiments to demonstrate DGIA’s performance across various SFL scenarios compared with other GIA schemes and show attack efficacy under general defenses.

Voice-enabled devices are becoming increasingly prevalent in the Internet of Things (IoT). Speech emotion recognition (SER), as a key technology in modern voice-assisted applications, holds tremendous potential for delivering convenient and intelligent services. Unfortunately, SER Service providers may not only analyze the emotions in users’ speech but also examine their speech content and voice characteristics, posing greater privacy risks. Existing real-time voice disguise methods, such as pitch scaling and VTLN, provide significant technical support for the protection of voiceprint privacy but significantly impact the accuracy of SER. In this paper, we propose a harmonic amplitude spectrum mapping (HASM) assisted voice disguise scheme, which disguises the voice for voiceprint privacy preservation while safeguarding the emotional information within the voice. Specifically, we first conduct an in-depth analysis of the features in the speech that can reflect emotions and find that restoring harmonic amplitude spectrum features after altering the speaker’s voice is crucial for recovering emotions in speech. Based on this discovery, we then preprocess the original speech signals with pitch scaling and design a HASM-assisted disguise scheme based on mathematical theory expression to restore the emotions. Our HASM-assisted voice disguise scheme is validated on the Berlin Emotional Speech Database, the LibriSpeech dataset and VCTK dataset. At voiceprint privacy protection levels of 81.86%, 85.42%, and 91.15% in the LibriSpeech dataset and 96.83%, 98.25%, and 98.41% in the VCTK dataset, respectively, the SER accuracy of acoustic feature-based disguised speech decreases by only 4.19%, 6.21%, and 9.87%, and the end-to-end SER accuracy decreases by only 3.69%, 7.37%, and 8.86%, which is superior to other voice disguise methods.

The proliferation and application of the Internet of Things (IoT) have significantly increased the production and processing of large volumes of images. Due to privacy concerns, such data are often encrypted before being outsourced to third parties for subsequent retrieval and processing. Existing encrypted image retrieval schemes primarily aim to improve search accuracy but are limited in terms of retrieval efficiency and storage expenses, rendering them challenging to be implemented on IoT devices. To address these issues, we propose a segmented hash-based privacy-preserving image retrieval (SHPIR) scheme that enables accurate and efficient retrieval of encrypted images in IoT networks. First, we propose a feature extraction model based on the convolutional neural network (CNN) to generate low-dimensional segmented hash codes that represent both image categories and features accurately. Next, we design the cryptographic hierarchical index structure based on the segmented hash codes to improve retrieval efficiency and accuracy. We also design a secure Hamming distance computation algorithm and employ the learning with errors (LWEs)-based secure k-nearest neighbor (kNN) algorithm to preserve the privacy of feature vectors and file-access patterns. Finally, we provide a security analysis verifying that the SHPIR scheme can protect image privacy as well as indexing and query privacy. Additionally, we constructed a real IoT environment to test the practical effectiveness and applicability of our scheme. Experimental evaluation indicates that our proposed scheme outperforms existing state-of-the-art schemes in retrieval accuracy, search efficiency, and storage costs, making it more suitable for real-world IoT applications.

Microphone has been widely integrated into mobile devices to provide physical basis for human-device voice interaction. However, the microphone may be spitefully invoked by maliciousmobile applications(apps) with arousing security and privacy concerns. In this work, to explore the issue of illegal microphone access, we develop spiteful apps through native and injection development to access the microphone viciously on a series of mobile devices. The results demonstrate that baleful apps could enable the microphone arbitrarily without any hint. To combat the unauthorized microphone access behavior, we design amicrophone illegal access detection(MicDet) scheme by constructing a request-response time model using the Unix time stamps of voice icon touched and microphone invoked. Through conducting numerical analysis and hypothesis testing to effectively verify the request-response pattern of app's normal access, we detect illegal access by analyzing whether the touch operation matches the normal pattern. For friendly user experience, we design an intuitive floating window to alert users by displaying the name of the app that illegally accessed the microphone once the illegal behavior is detected. Finally, we apply our scheme to different mobile devices and test several apps, the experimental results show that the MicDet scheme achieves a high detection accuracy.

Millions of mobile devices are currently equipped withvoice assistant(VA) for robust identity authentication. Regrettably, VA authentication remains susceptible to voice spoofing attacks, encompassing playback, synthesis, and conversion attacks. Despite numerous proposed defense schemes, these solutions exhibit deficiencies such as limited versatility and cumbersome implementation. Many are specialized in detecting only one specific type of attack, necessitate additional equipment, or mandate placing the device in specific locations. In this study, we introduce a versatile and user-friendly scheme designed to counteract voice spoofing attacks by analyzing common nonlinear features inherent in vocalization systems. Initially, we demonstrate the nonlinear nature of both human and mobile device vocalization by scrutinizing the mechanisms and processes of voice generation. Subsequently, we develop a comprehensive nonlinear model and extract a universal acoustic nonlinear property to discern sounds produced by humans from those generated by loudspeakers, thereby enhancing resistance against spoofing attacks. Finally, we conduct extensive experiments utilizing a real-world collected dataset and the supplementary ASVspoof2017 dataset. Evaluation results reveal that the proposed scheme significantly improves accuracy and computation cost by nearly 40% and 15%, respectively.

Due to the sensitive and confidential nature of healthcare data, it cannot be freely transmitted, resulting in the challenge of data silos. While federated learning offers a solution to this data island dilemma, it also faces potential threats from malicious client attacks. The system becomes more vulnerable when dealing with non-independent and identically distributed (non-IID) data. Hence, a robust federated learning framework is indispensable to defend against malicious attacks. In this study, we employ a dynamic feature extractor based on the sparse representation, and the parameters of each iteration construct the feature extractor for the subsequent parameters. Then, we use optimized k-means clustering to get benign clients and aggregate them. The experimental results show that the system robustness is lower for non-IID datasets compared to IID healthcare datasets. And our RobustHealthFL can significantly enhance the robustness of the system when facing non-IID data. Our code is available at https://github.com/xipengp/RobustHealthFL.

Enormous mobile applications (apps) now support voice functionality for convenient user-device interaction. However, these voice-enabled apps may spitefully invoke microphone to realize voice eavesdropping with arousing security risks and privacy concerns. To explore the issue of voice eavesdropping, in this work, we first design eavesdropping apps through native development and injection development to conduct eavesdropping attacks on a series of smart devices. The results demonstrate that eavesdropping could be carried out freely without any hint. To thwart voice eavesdropping, we propose a valid eavesdropping detection (EarDet) scheme based on the discovery that the activation of voice function in most apps requires authorization from the user by touching a specific voice icon. In the scheme, we construct a request-response time model using the Unix time stamps of touching the voice icon and microphone invoked. Through numerical analysis and hypothesis testing to effectively verify the pattern of the app’s normal access under user authorization to the microphone, we could detect eavesdropping attacks by sensing whether there is a touch operation. Finally, we apply the scheme to different smart devices and test several apps. The experimental results show that the proposed EarDet scheme can achieve a high detection accuracy.

Bothvoice communicationand automatic speech verification (ASV) over smart devices are vulnerable to the voice impersonation (VI) attack, which is often launched via imitating a target’s voice characteristics to deceive human auditory sense or fool the ASV system. Researchers have designed a number of defense schemes yet without the consideration of universality due to the lack of comprehensive data sets. In this article, we propose a universal defense scheme based on the VI data set collected from a famous TV show named “The Sound.” First, we deliver a thorough study on the VI attacks in both auditory and ASV systems to verify the collected simulated voice could spoof the auditory and the ASV system with a notable probability. Second, we propose a quasi-Gaussian distribution (QGD)-based defense scheme with the discovery about specific voice characteristics that are distinct between attackers and targets. Finally, we conduct extensive experimental results on our collected VI data set as well as the auxiliary ASVspoof2017 data set, to indicate the proposed QGD scheme outperforms the state-of-the-art schemes: backpropagation neural network, support vector machine, and Gaussian mixture model, in terms of accuracy.

Mobile crowdsensing is an emerging paradigm that selects users to complete sensing tasks. Recently, mobile vehicles are adopted to perform sensing data collection tasks in the urban city due to their ubiquity and mobility. In this article, we study how mobile vehicles can be optimally selected in order to collect maximum data from the urban environment in a future period of tens of minutes. We formulate the recruitment of vehicles as a maximum data limited budget problem. The application scenario is generalized to a realistic online setting where vehicles are continuously moving in real-time and the data center decides to recruit a set of vehicles immediately. A deep learning-based scheme through mobile vehicles (DLMV) is proposed to collect sensing data in the urban environment. We first propose a deep learning-based offline algorithm to predict vehicle mobility in a future time period. Furthermore, we propose a greedy online algorithm to recruit a subset of vehicles with a limited budget for the NP-Complete problem. Extensive experimental evaluations are conducted on the real mobility dataset in Rome. The results have not only verified the efficiency of our proposed solution but also validated that DLMV can improve the quantity of collected sensing data compared with other algorithms.

In this paper, we consider the issue of the secure transmissions for the cognitive radio-based Internet of Medical Things (IoMT) with wireless energy harvesting. In these systems, a primary transmitter (PT) will transmit its sensitive medical information to a primary receiver (PR) by a multi-antenna-based secondary transmitter (ST), where we consider that a potential eavesdropper may listen to the PT’s sensitive information. Meanwhile, the ST also transmits its own information concurrently by utilizing spectrum sharing. We aim to propose a novel scheme for jointly designing the optimal parameters, i.e., energy harvesting (EH) time ratio and secure beamforming vectors, for maximizing the primary secrecy transmission rate while guaranteeing secondary transmission requirement. For solving the nonconvex optimization problem, we transfer the problem into convex optimization form by adopting the semidefinite relaxation (SDR) method and Charnes–Cooper transformation technique. Then, the optimal secure beamforming vectors and energy harvesting duration can be obtained easily by utilizing the CVX tools. According to the simulation results of secrecy transmission rate, i.e., secrecy capacity, we can observe that the proposed protocol for the considered system model can effectively promote the primary secrecy transmission rate when compared with traditional zero-forcing (ZF) scheme, while ensuring the transmission rate of the secondary system.

With rapid development of e-healthcare systems, patients that are equipped with resource-limited e-healthcare devices (Internet of Things) generate huge amount of health data for health management. These health data possess significant medical value when aggregated from these distributed devices. However, efficient health data aggregation poses several security and privacy issues such as confidentiality disclosure and differential attacks, as well as patients may be reluctant to contribute their health data for aggregation. In this paper, we propose a privacy-preserving heath data aggregation scheme that securely collects health data from multiple sources and guarantee fair incentives for contributing patients. Specifically, we employ signature techniques to keep fair incentives for patients. Meanwhile, we add noises into the health data for differential privacy. Furthermore, we combine Boneh-Goh-Nissim cryptosystem and Shamir's secret sharing to keep data obliviousness security and fault tolerance. Security and privacy discussions show that our scheme can resist differential attacks, tolerate healthcare centers failures, and keep fair incentives for patients. Performance evaluations demonstrate cost-efficient computation, communication and storage overhead.

Pervasive data collected from e-healthcare devices possess significant medical value through data sharing with professional healthcare service providers. However, health data sharing poses several security issues, such as access control and privacy leakage, as well as faces critical challenges to obtain efficient data analysis and services. In this article, we propose an efficient and privacy-preserving fog-assisted health data sharing (PFHDS) scheme for e-healthcare systems. Specifically, we integrate the fog node to classify the shared data into different categories according to disease risks for efficient health data analysis. Meanwhile, we design an enhanced attribute-based encryption method through combination of a personal access policy on patients and a professional access policy on the fog node for effective medical service provision. Furthermore, we achieve significant encryption consumption reduction for patients by offloading a portion of the computation and storage burden from patients to the fog node. Security discussions show that PFHDS realizes data confidentiality and fine-grained access control with collusion resistance. Performance evaluations demonstrate cost-efficient encryption computation, storage and energy consumption.

In Body Area Networks (BANs), bio-sensors can collect personal health information and cooperate with each other to provide intelligent health care services for medical users. Since personal health information is highly privacy-sensitive, the flourish of BANs still faces critical security challenges, especially secure communication between bio-sensors. In this paper, we propose a flexible and efficient authenticated key agreement scheme (PBAKA) to provide secure communication for BANs. Specifically, we employ a control unit (e.g., smart phone) to launch authentication based on physiological features collected from BANs, and integrate bilinear pairings to negotiate session keys for bio-sensors. Since physiological features can be collected from various kinds of bio-sensors in real time, PBAKA is flexible for adding new bio-sensors without pre-distributed keys. Meanwhile, PBAKA is computationally efficient by offloading authentication burden from resource-limited bio-sensors to the control unit. Security analysis demonstrates that PBAKA is provably secure under the decisional bilinear Diffie-Hellman assumption. Extensive experimental results validate efficient communication, computation and energy consumption of our scheme when compared with several existing solutions.

Social Media Health Networks provide a promising paradigm to attract patients to share and communicate their personal health status with other online patients, and consult healthcare services from online caregivers with social networks. Social Media Health Networks transform healthcare services from time-consuming offline hospital-centered paradigm to the convenient and efficient online paradigm through Internet, which can expand the traditional healthcare services and shorten the information gap between patients and caregivers. However, how to build the trust between patients and caregivers raises a challenging issue due to the openness of the social networks; meanwhile, the personal privacy may be disclosed when sharing personal health information with other patients and caregivers. In this paper, we propose a personalized and trusted healthcare service approach to enable trusted and privacy-preserving healthcare services in social media health networks, which can improve the trustiness between patients and caregivers through authentic ratings toward caregivers and guarantee the patients' privacy. Specifically, we employ the collaborative filtering model to seek appropriate personalized caregivers, bloom filter to extract and map the personal healthcare symptoms, and inner product to compute the similarity between patients for finding patients with similar health symptoms in a privacy-preserving way. Meanwhile, to guarantee authentic ratings and reviews toward caregivers, we develop a sybil attack detection scheme to find patients' fake ratings and reviews using different pseudonyms. Security analysis shows that our proposed approach can preserve the privacy of patients and prevent sybil attacks. Performance evaluation demonstrates that our approach can achieve prominent performance improvement, in terms of personalized caregivers finding and sybil attack resistance.

With the advancements of electronic medical equipment, e-healthcare system becomes a promising paradigm to continuously monitor health conditions and remotely diagnose phenomena. Meanwhile, it generates a large volume of health data and poses several security challenges, such as access control and privacy leakage. In this paper, we propose a lightweight and privacy- preserving fog-assisted information sharing scheme (PFHD) for health big data. Specifically, we integrate fog computing into e-healthcare system to pre-process the raw health data and improve the efficiency of health data analysis. Furthermore, to prevent privacy leakage, we design a hierarchical attribute-based encryption method by encrypting the profile and health data with different access policies. In addition, we reduce the computation cost on devices by offloading health data encryption from devices to fog servers. Security discussions show that PFHD can achieve fine- grained health data sharing with privacy preservation. Performance evaluations demonstrate the efficiency of PFHD, especially in terms of encryption computation and storage costs.