More Like this

1. Glyph: Fast and Accurately Training Deep Neural Networks on Encrypted Data

   Qian, Lou; Bo, Feng; Geoffrey, Fox; Lei, Jiang (October 2020, Advances in neural information processing systems)

   null (Ed.)

   Because of the lack of expertise, to gain benefits from their data, average users have to upload their private data to cloud servers they may not trust. Due to legal or privacy constraints, most users are willing to contribute only their encrypted data, and lack interests or resources to join deep neural network (DNN) training in cloud. To train a DNN on encrypted data in a completely non-interactive way, a recent work proposes a fully homomorphic encryption (FHE)-based technique implementing all activations by \textit{Brakerski-Gentry-Vaikuntanathan} (BGV)-based lookup tables. However, such inefficient lookup-table-based activations significantly prolong private training latency of DNNs. In this paper, we propose, Glyph, an FHE-based technique to fast and accurately train DNNs on encrypted data by switching between TFHE (Fast Fully Homomorphic Encryption over the Torus) and BGV cryptosystems. Glyph uses logic-operation-friendly TFHE to implement nonlinear activations, while adopts vectorial-arithmetic-friendly BGV to perform multiply-accumulations (MACs). Glyph further applies transfer learning on DNN training to improve test accuracy and reduce the number of MACs between ciphertext and ciphertext in convolutional layers. Our experimental results show Glyph obtains state-of-the-art accuracy, and reduces training latency by 69%~99% over prior FHE-based privacy-preserving techniques on encrypted datasets. 

   more » « less
2. Federated Learning on Distributed and Encrypted Data for Smart Manufacturing

   https://doi.org/10.1115/1.4065571  

   Kuo, Timothy; Yang, Hui (July 2024, Journal of Computing and Information Science in Engineering)

   Abstract Industry 4.0 drives exponential growth in the amount of operational data collected in factories. These data are commonly distributed and stored in different business units or cooperative companies. Such data-rich environments increase the likelihood of cyber attacks, privacy breaches, and security violations. Also, this poses significant challenges on analytical computing on sensitive data that are distributed among different business units. To fill this gap, this article presents a novel privacy-preserving framework to enable federated learning on siloed and encrypted data for smart manufacturing. Specifically, we leverage fully homomorphic encryption (FHE) to allow for computation on ciphertexts and generate encrypted results that, when decrypted, match the results of mathematical operations performed on the plaintexts. Multilayer encryption and privacy protection reduce the likelihood of data breaches while maintaining the prediction performance of analytical models. Experimental results in real-world case studies show that the proposed framework yields superior performance to reduce the risk of cyber attacks and harness siloed data for smart manufacturing. 

   more » « less
3. Privacy-Preserving Data-Driven Learning Models for Emerging Communication Networks: A Comprehensive Survey

   https://doi.org/10.1109/COMST.2024.3486690  

   Fouda, Mostafa M; Fadlullah, Zubair Md; Ibrahem, Mohamed I; Kato, Nei (October 2024, IEEE Communications Surveys & Tutorials)

   With the proliferation of Beyond 5G (B5G) communication systems and heterogeneous networks, mobile broadband users are generating massive volumes of data that undergo fast processing and computing to obtain actionable insights. While analyzing this huge amount of data typically involves machine and deep learning-based data-driven Artificial Intelligence (AI) models, a key challenge arises in terms of providing privacy assurances for user-generated data. Even though data-driven techniques have been widely utilized for network traffic analysis and other network management tasks, researchers have also identified that applying AI techniques may often lead to severe privacy concerns. Therefore, the concept of privacy-preserving data-driven learning models has recently emerged as a hot area of research to facilitate model training on large-scale datasets while guaranteeing privacy along with the security of the data. In this paper, we first demonstrate the research gap in this domain, followed by a tutorial-oriented review of data-driven models, which can be potentially mapped to privacy-preserving techniques. Then, we provide preliminaries of a number of privacy-preserving techniques (e.g., differential privacy, functional encryption, Homomorphic encryption, secure multi-party computation, and federated learning) that can be potentially adopted for emerging communication networks. The provided preliminaries enable us to showcase the subset of data-driven privacy-preserving models, which are gaining traction in emerging communication network systems. We provide a number of relevant networking use cases, ranging from the B5G core and Radio Access Networks (RANs) to semantic communications, adopting privacy-preserving data-driven models. Based on the lessons learned from the pertinent use cases, we also identify several open research challenges and hint toward possible solutions. 

   more » « less
4. Testing Robustness of Homomorphically Encrypted Split Model LLMs

   https://doi.org/10.23919/DATE64628.2025.10992988  

   Folkerts, Lars Wolfgang; Tsoutsos, Nektarios Georgios (May 2025, IEEE)

   Large language models (LLMs) have recently transformed many industries, enhancing content generation, customer service agents, data analysis, and even software generation. These applications are often hosted on remote servers to protect the neural-network model IP; however, this raises concerns about the privacy of input queries. Fully Homomorphic Encryption (FHE), an encryption technique that allows computations on private data, has been proposed as a solution to this challenge. Nevertheless, due to the increased size of LLMs and the computational overheads of FHE, today's practical FHE LLMs are implemented using a split model approach. Here, a user sends their FHE encrypted data to the server to run an encrypted attention head layer; then the server returns the result of the layer for the user to run the rest of the model locally. By employing this method, the server maintains part of their model IP, while the user still gets to perform private LLM inference. In this work, we evaluate the neural-network model IP protections of single-layer split model LLMs, and demonstrate a novel attack vector that makes it easy for a user to extract the neural network model IP from the server, bypassing the claimed protections for encrypted computation. In our analysis, we demonstrate the feasibility of this attack, and discuss potential mitigations. 

   more » « less
5. Privacy-Preserving Driver Monitoring on the Edges: Transformer-Based Processing of Secret Shares from Video Streams

   https://doi.org/10.1145/3777384  

   Bai, Tianyu; Shao, Danyang; He, Ying; Yang, Qing; Feng, Yunhe; Fu, Song (December 2025, ACM Transactions on Internet of Things)

   Modern vehicles increasingly rely on advanced driver monitoring systems (DMS) to ensure safety and enhance the driving experience. These systems assess driver status to prevent accidents caused by fatigue, inattentiveness, or intoxication. While some DMS applications process video data on vehicle, many rely on edge or cloud-based solutions, raising significant privacy concerns due to the storage of sensor data from vehicles. Existing approaches, such as de-identification and homomorphic encryption, either impose heavy computational overhead on vehicles or insufficiently address privacy. To overcome these limitations, we present the Privacy-preserving Driver Monitoring System (PDMS), a novel framework based on the additive secret sharing theory and privacy-preserving Transformer-based deep learning models. PDMS creates randomized secret shares from driver’s facial video data on vehicle, processes them independently through privacy-preserving Transformer models on edges, and securely aggregates partial results on vehicle, ensuring vehicles’ sensor data and final results remain protected. This approach reduces the computational load on the vehicle, enabling cost-effective and scalable DMS solutions that protect the privacy of the driver both in transit and in processing. Our contributions include the design and optimization of the PDMS system, incorporating privacy-preserving DNN layers that are capable of processing randomized secret shares. Furthermore, we present a practical system that utilizes a vision transformer (ViT)-based gaze estimation model, demonstrating the effectiveness of PDMS through comprehensive experiments. 

   more » « less