Experiments show that Sarus improves scene-level coverage by effectively aggregating complementary detections, particularly in distance-dependent regimes where individual modalities degrade, and indicate that privacy-preserving multi-vendor perception fusion is feasible for real-time deployment when statistical compression and spatial sparsity are jointly exploited.
Abstract
Cooperative perception enables autonomous vehicles (AVs) to improve situational awareness by aggregating detection outputs from multiple agents and sensing platforms, often via a shared fusion service in multi-vendor deployments. However, sharing such outputs at inference time exposes proprietary model behavior and sensitive environmental information, creating significant privacy and security concerns. In this paper, we present Sarus, a privacy-preserving framework for multi-vendor perception fusion via homomorphic encryption (HE), enabling aggregation without revealing individual vendor outputs. Each vendor encodes detections as compact Gaussian moment vectors over a shared spatial lattice and transmits encrypted payloads to a fusion server, which aggregates them directly in the encrypted domain. The fused result is then decrypted and reconstructed into final detections through class-wise bin merging. We analyze the computational complexity, showing linear scaling for vendor payload construction and $O(BV)$ server-side fusion with the number of occupied bins $B$ and vendors $V$, while postprocessing scales as $O(B + \sum_{c\in \mathcal{C}} B_c^2)$, where $\mathcal{C}$ denotes the set of object classes and $B_c$ is the number of occupied bins for class $c$. Experiments demonstrate linear scaling in practice with only a bounded constant-factor overhead from HE, with decryption dominating postprocessing cost. Experiments on the KITTI dataset using camera (YOLOv8) and LiDAR (PointPillars, PV-RCNN) detectors show that Sarus improves scene-level coverage by effectively aggregating complementary detections, particularly in distance-dependent regimes where individual modalities degrade. These results indicate that privacy-preserving multi-vendor perception fusion is feasible for real-time deployment when statistical compression and spatial sparsity are jointly exploited.
Space-Air-Ground Integrated Networks (SAGINs) represent a revolutionary paradigm to attain seamless and ubiquitous connectivity by incorporating space-based, aerial, and ground communication systems. Semantic communication in SAGINs is a promise to improve transmission efficiency by conveying only the meaning of data rather than raw bits. However, there are risks associated with transmitting semantic-rich data over insecure channels. Sensitive information leakage poses security challenges for node-to-node semantic communications. This paper addresses this problem when face images are transmitted over wireless channels in the presence of an illegitimate receiver. The paper proposes a new semantic communication approach that ensures privacy by applying selective homomorphic encryption (SHE) for protection and deprotection. The scheme represents a cutting-edge direction that blends privacy-preserving computation with deep visual understanding. The proposed system leverages the potential of channel and spatial attention (CSA) mechanisms for communicating nodes’ architectures and optimization. It exploits the selective homomorphic encryption for facial landmarks-aware encryption, where feature-level adaptivity is employed to ensure semantic information is securely conveyed from the high-altitude platform station (HAPS) node to the legitimate receiver on the ground. Simulation findings indicate the proposed scheme’s efficiency in preventing ground illegitimate receivers from reconstructing valuable face regions of interest (ROIs) while ensuring high-fidelity legitimate full image reconstruction. Furthermore, the proposed system reveals that applying attention mechanisms and encrypting only semantic features of interest can lead to lower processing and communication costs.
Pascal Nkurunziza, D. Umehara· IEEE Open Journal of the Com...· 0 citations
SVIiT is described as communication-reduced relative to the evaluated MPC baselines rather than universally lightweight, and its present practical scope is primarily high-bandwidth LAN or provider-edge deployments.
Tingting Chen· ICST Transactions on Scalabl...· 0 citations
The consumer Internet of Things (CIoT) enables large-scale sensing and data-driven services by connecting billions of devices. However, the privacy-preserving data aggregation in mobile edge computing (MEC)-enabled CIoT remains challenging when the edge aggregator is malicious, rather than simply honest-but-curious. Specifically, a malicious MEC server can selectively drop user reports or tamper with ciphertexts, undermining data integrity and ownership. To address this, we propose a verifiable and fault-tolerant privacy-preserving aggregation scheme. By substituting computationally intensive homomorphic encryption (HE) with a double-masking mechanism and integrating bilinear pairing-based accumulators, the proposed scheme provides resilience against tampering and deletion attacks while ensuring data privacy. The design supports user dropouts within a single reporting round without requiring interactive recovery, enabling each device to locally audit the inclusion of the corresponding ciphertext via a compact membership witness. Theoretical analysis and experimental results demonstrate that the proposed scheme reduces communication overhead and payload size. It satisfies the security requirements of CIoT ecosystems and offers a practical tradeoff between security and efficiency for latency-sensitive deployments.
Jianhong Zhang, Miao Xue, Xinyu Bai· IEEE Internet of Things Jour...· 0 citations
Image fusion integrates complementary multi-source visual information, yet plaintext fusion poses severe privacy risks. Conventional lattice-based homomorphic encryption enables ciphertext computation but incurs substantial computational overhead and exhibits poor compatibility with image fusion tasks. This work investigates lightweight privacy-preserving image fusion built upon pixel scrambling. Any pixel-scrambling technique that only rearranges pixel coordinates without modifying pixel values inherently satisfies the homomorphic properties required for pixel-level spatial fusion. In this paper, we adopt full-size random permutation matrix scrambling as a representative pixel-disordering method for systematic theoretical and experimental verification. The scheme generates a secret key matching the resolution of test images; it merely reorders pixel positions while preserving all original intensity values, allowing direct cipher-domain fusion that yields distortion-free outputs for averaging, weighted averaging, maximum-value and minimum-value fusion rules. Free from intricate lattice calculations and ciphertext expansion, the proposed lightweight framework achieves an optimal trade-off among security, computational efficiency and fusion quality for cloud computing scenarios.
Cloud computing offers organizations scalable storage and computation, but outsourcing data processing to third-party infrastructure introduces serious privacy and confidentiality risks. Two complementary paradigms have emerged to address this challenge: homomorphic encryption (HE), which allows computation directly on encrypted data, and federated learning (FL), which enables collaborative model training without centralizing raw data. This paper presents a structured review of privacy-preserving data processing techniques for cloud environments built on HE and FL, individually and in hybrid combination. We propose a taxonomy of existing approaches, synthesize representative literature in a comparative table, illustrate a generic hybrid HE-FL architecture, and evaluate the two paradigms against criteria including data exposure, computational overhead, communication cost, resistance to inference attacks, and cloud deployment readiness. We further identify open challenges — including computational latency, key management, non-IID data distributions, and standardization gaps — and outline promising directions for future research, such as hardware-accelerated HE, adaptive encryption granularity, and standardized hybrid privacy frameworks for cloud-native machine learning.
Shivendra Shukla, Chandra Shekhar Gautam, Divyansh Tiwari· International Journal of Cre...· 0 citations
With the rapid evolution of 5G communications, artificial intelligence, and new energy technologies, intelligent driving has become a pivotal component of modern transportation infrastructure. However, the openness and inherent complexity of the Internet of Vehicles (IoV) pose significant challenges to data privacy and security. While Federated Learning (FL) facilitates collaborative training of data models without requiring raw data to leave local devices, its centralized aggregation architecture struggles to address privacy concerns in cross-trust domain collaborations and fails to effectively handle the challenges posed by vehicle node mobility. In this paper, we investigate cross-trust domain collaborative federated learning within the IoV and construct a privacy-preserving Cloud-Edge-End architecture based on Fully Homomorphic Encryption (FHE). To address the dynamic nature of vehicle nodes, we propose a hybrid privacy-preserving scheme that integrates Threshold Fully Homomorphic Encryption (ThFHE) and Multi-Key Fully Homomorphic Encryption (MKFHE). The experimental results indicate that the proposed collaborative architecture is theoretically reasonable. In addition, the scheme effectively achieves collaborative model training while maintaining security at the privacy protection level and supporting seamless vehicle mobility.
Bo-Ya Liu, Guosheng Xu, Chenyu Wang et al.· Electronics· 0 citations
