Functional Encryption in Secure Neural Network Training: Data Leakage and Practical Mitigations

• URL: http://arxiv.org/abs/2509.21497v1
• Date: Thu, 25 Sep 2025 19:56:05 GMT
• Title: Functional Encryption in Secure Neural Network Training: Data Leakage and Practical Mitigations
• Abstract summary: We present an attack on neural networks that uses Functional Encryption (FE) for secure training over encrypted data.<n>One approach ensures security without relying on encryption, while the other uses function-hiding inner-product techniques.
• Score: 45.88028371034407
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: With the increased interest in artificial intelligence, Machine Learning as a Service provides the infrastructure in the Cloud for easy training, testing, and deploying models. However, these systems have a major privacy issue: uploading sensitive data to the Cloud, especially during training. Therefore, achieving secure Neural Network training has been on many researchers' minds lately. More and more solutions for this problem are built around a main pillar: Functional Encryption (FE). Although these approaches are very interesting and offer a new perspective on ML training over encrypted data, some vulnerabilities do not seem to be taken into consideration. In our paper, we present an attack on neural networks that uses FE for secure training over encrypted data. Our approach uses linear programming to reconstruct the original input, unveiling the previous security promises. To address the attack, we propose two solutions for secure training and inference that involve the client during the computation phase. One approach ensures security without relying on encryption, while the other uses function-hiding inner-product techniques.

Related papers

• A Selective Homomorphic Encryption Approach for Faster Privacy-Preserving Federated Learning [2.942616054218564]
  Federated learning (FL) has come forward as a critical approach for privacy-preserving machine learning in healthcare.<n>Current security implementations for these systems face a fundamental trade-off: rigorous cryptographic protections impose prohibitive computational overhead.<n>We present Fast and Secure Federated Learning, a novel approach that strategically combines selective homomorphic encryption, differential privacy, and bitwise scrambling to achieve robust security.
  arXiv  Detail & Related papers  (2025-01-22T14:37:44Z)
• Privacy-Preserving Cyberattack Detection in Blockchain-Based IoT Systems Using AI and Homomorphic Encryption [22.82443900809095]
  This work proposes a privacy-preserving cyberattack detection framework for blockchain-based Internet-of-Things (IoT) systems.<n>In our approach, artificial intelligence (AI)-driven detection modules are strategically deployed at blockchain nodes to identify real-time attacks.<n>To safeguard privacy, the data is encrypted using homomorphic encryption (HE) before transmission.<n>Our simulation results demonstrate that our proposed method can not only mitigate the training time but also achieve detection accuracy that is approximately identical to the approach without encryption, with a gap of around 0.01%.
  arXiv  Detail & Related papers  (2024-12-18T05:46:53Z)
• PriPHiT: Privacy-Preserving Hierarchical Training of Deep Neural Networks [44.0097014096626]
  We propose a method to perform the training phase of a deep learning model on both an edge device and a cloud server.<n>The proposed privacy-preserving method uses adversarial early exits to suppress the sensitive content at the edge and transmits the task-relevant information to the cloud.
  arXiv  Detail & Related papers  (2024-08-09T14:33:34Z)
• Homomorphic Encryption-Enabled Federated Learning for Privacy-Preserving Intrusion Detection in Resource-Constrained IoV Networks [20.864048794953664]
  This paper proposes a novel framework to address the data privacy issue for Federated Learning (FL)-based Intrusion Detection Systems (IDSs) in Internet-of-Vehicles (IoVs) with limited computational resources. We first propose a highly-effective framework using homomorphic encryption to secure data that requires offloading to a centralized server for processing. We develop an effective training algorithm tailored to handle the challenges of FL-based systems with encrypted data.
  arXiv  Detail & Related papers  (2024-07-26T04:19:37Z)
• Security and Privacy Issues and Solutions in Federated Learning for Digital Healthcare [0.0]
  We present vulnerabilities, attacks, and defenses based on the widened attack surfaces of Federated Learning. We suggest promising new research directions toward a more robust FL.
  arXiv  Detail & Related papers  (2024-01-16T16:07:53Z)
• Hierarchical Training of Deep Neural Networks Using Early Exiting [42.186536611404165]
  Deep neural networks provide state-of-the-art accuracy for vision tasks but they require significant resources for training. Deep neural networks are trained on cloud servers far from the edge devices that acquire the data. In this study, a novel hierarchical training method for deep neural networks is proposed that uses early exits in a divided architecture between edge and cloud workers.
  arXiv  Detail & Related papers  (2023-03-04T11:30:16Z)
• Pre-trained Encoders in Self-Supervised Learning Improve Secure and Privacy-preserving Supervised Learning [63.45532264721498]
  Self-supervised learning is an emerging technique to pre-train encoders using unlabeled data. We perform first systematic, principled measurement study to understand whether and when a pretrained encoder can address the limitations of secure or privacy-preserving supervised learning algorithms.
  arXiv  Detail & Related papers  (2022-12-06T21:35:35Z)
• SoK: Privacy-preserving Deep Learning with Homomorphic Encryption [2.9069679115858755]
  homomorphic encryption (HE) can be performed on encrypted data without revealing its content. We take an in-depth look at approaches that combine neural networks with HE for privacy preservation. We find numerous challenges to HE based privacy-preserving deep learning such as computational overhead, usability, and limitations posed by the encryption schemes.
  arXiv  Detail & Related papers  (2021-12-23T22:03:27Z)
• Reinforcement Learning on Encrypted Data [58.39270571778521]
  We present a preliminary, experimental study of how a DQN agent trained on encrypted states performs in environments with discrete and continuous state spaces. Our results highlight that the agent is still capable of learning in small state spaces even in presence of non-deterministic encryption, but performance collapses in more complex environments.
  arXiv  Detail & Related papers  (2021-09-16T21:59:37Z)
• Faster Secure Data Mining via Distributed Homomorphic Encryption [108.77460689459247]
  Homomorphic Encryption (HE) is receiving more and more attention recently for its capability to do computations over the encrypted field. We propose a novel general distributed HE-based data mining framework towards one step of solving the scaling problem. We verify the efficiency and effectiveness of our new framework by testing over various data mining algorithms and benchmark data-sets.
  arXiv  Detail & Related papers  (2020-06-17T18:14:30Z)
• A Privacy-Preserving Distributed Architecture for Deep-Learning-as-a-Service [68.84245063902908]
  This paper introduces a novel distributed architecture for deep-learning-as-a-service. It is able to preserve the user sensitive data while providing Cloud-based machine and deep learning services.
  arXiv  Detail & Related papers  (2020-03-30T15:12:03Z)
• CryptoSPN: Privacy-preserving Sum-Product Network Inference [84.88362774693914]
  We present a framework for privacy-preserving inference of sum-product networks (SPNs) CryptoSPN achieves highly efficient and accurate inference in the order of seconds for medium-sized SPNs.
  arXiv  Detail & Related papers  (2020-02-03T14:49:18Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.