Privacy-Preserving Robustness Verification for Neural Networks

• URL: http://arxiv.org/abs/2607.05251v1
• Date: Mon, 06 Jul 2026 15:59:17 GMT
• Title: Privacy-Preserving Robustness Verification for Neural Networks
• Abstract summary: We introduce SecureCROWN, the first framework for privacy-preserving neural network verification.<n>Our framework enables a model owner and a data owner to jointly compute certified robustness bounds.<n>We show that SecureCROWN strictly matches verification results, while completing in 0.1--200s across varied model sizes.
• Score: 8.136747065885006
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Neural network verification and data privacy are inherently in tension: verification demands full access to model parameters and input data, yet both are increasingly restricted by privacy regulations and intellectual property constraints. This tension has left robustness verification impractical in privacy-sensitive domains. In this work, we address this gap with SecureCROWN, the first framework for privacy-preserving neural network robustness verification. Built upon secure two-party computation (2PC), our framework enables a model owner and a data owner to jointly compute certified robustness bounds -- revealing only the final result while provably protecting both parties' private data under the semi-honest security model. A key challenge is securely computing the conditional operations in Linear Bound Propagation, where the data-dependent branching is incompatible with standard secure computation protocols. We eliminate branching by formulating conditional logic as continuous arithmetic operations. Additionally, we introduce a Newton--Raphson refinement method to improve numerical stability. Extensive analysis and experiments show that SecureCROWN strictly matches plaintext verification results, while completing in 0.1--200s across varied model sizes and communication settings (LAN/WAN), demonstrating the feasibility of privacy-preserving neural network verification.

Related papers

• Hybrid Robustness Verification for Spatio-Temporal Neural Networks [19.026662893450425]
  Existing verification methods rely on overly conservative approximations or incur prohibitive computational costs.<n>In practice, adversarial perturbations exhibit structured spatial and temporal correlations, constrained to lower-dimensional, semantically meaningful subspaces.<n>We study robustness verification 3D CNNs processing video inputs, targeting applications in action recognition (UCF-101), autonomous driving (Udacity), medical imaging (MedMNIST)
  arXiv  Detail & Related papers  (2026-06-08T17:06:51Z)
• Byzantine-Robust and Differentially Private Federated Optimization under Weaker Assumptions [89.52532304099522]
  Federated Learning (FL) enables clients to collaboratively train a shared model without centralizing their raw data, offering an inherent level of privacy.<n> gradients and model updates can still leak sensitive information, while malicious servers may mount adversarial attacks such as Byzantine manipulation.<n>These vulnerabilities highlight the need to address differential privacy (DP) and Byzantine robustness within a unified framework.<n>We propose Byz-Clip21-SGD2M, a new algorithm that integrates robust aggregation with double momentum and carefully designed clipping.
  arXiv  Detail & Related papers  (2026-03-24T17:39:09Z)
• A Secure and Private Distributed Bayesian Federated Learning Design [56.92336577799572]
  Distributed Federated Learning (DFL) enables decentralized model training across large-scale systems without a central parameter server.<n>DFL faces three critical challenges: privacy leakage from honest-but-curious neighbors, slow convergence due to the lack of central coordination, and vulnerability to Byzantine adversaries aiming to degrade model accuracy.<n>We propose a novel DFL framework that integrates Byzantine robustness, privacy preservation, and convergence acceleration.
  arXiv  Detail & Related papers  (2026-02-23T16:12:02Z)
• Perfectly-Private Analog Secure Aggregation in Federated Learning [51.61616734974475]
  In federated learning, multiple parties train models locally and share their parameters with a central server, which aggregates them to update a global model.<n>In this paper, a novel secure parameter aggregation method is proposed that employs the torus rather than a finite field.
  arXiv  Detail & Related papers  (2025-09-10T15:22:40Z)
• On the MIA Vulnerability Gap Between Private GANs and Diffusion Models [51.53790101362898]
  Generative Adversarial Networks (GANs) and diffusion models have emerged as leading approaches for high-quality image synthesis.<n>We present the first unified theoretical and empirical analysis of the privacy risks faced by differentially private generative models.
  arXiv  Detail & Related papers  (2025-09-03T14:18:22Z)
• ZTFed-MAS2S: A Zero-Trust Federated Learning Framework with Verifiable Privacy and Trust-Aware Aggregation for Wind Power Data Imputation [8.934430272818048]
  Wind power data often suffers from missing values due to sensor faults and unstable transmission at edge sites.<n>ZTFed-MAS2S is a zero-trust federated learning framework that integrates a sequence-to-sequence imputation model.<n>Experiments on real-world wind farm datasets validate the superiority of ZTFed-MAS2S in both federated learning performance and missing data imputation.
  arXiv  Detail & Related papers  (2025-08-24T01:50:58Z)
• Towards Trustworthy AI: Secure Deepfake Detection using CNNs and Zero-Knowledge Proofs [0.0]
  TrustDefender is a framework that detects deepfake imagery in real-time extended reality (XR) streams.<n>Our work establishes a foundation for reliable AI in immersive and privacy-sensitive applications.
  arXiv  Detail & Related papers  (2025-07-22T20:47:46Z)
• PriRoAgg: Achieving Robust Model Aggregation with Minimum Privacy Leakage for Federated Learning [49.916365792036636]
  Federated learning (FL) has recently gained significant momentum due to its potential to leverage large-scale distributed user data.<n>The transmitted model updates can potentially leak sensitive user information, and the lack of central control of the local training process leaves the global model susceptible to malicious manipulations on model updates.<n>We develop a general framework PriRoAgg, utilizing Lagrange coded computing and distributed zero-knowledge proof, to execute a wide range of robust aggregation algorithms while satisfying aggregated privacy.
  arXiv  Detail & Related papers  (2024-07-12T03:18:08Z)
• Enabling Privacy-preserving Model Evaluation in Federated Learning via Fully Homomorphic Encryption [1.9662978733004604]
  Federated learning has become increasingly widespread due to its ability to train models collaboratively without centralizing sensitive data.<n>The evaluation phase presents significant privacy risks that have not been adequately addressed in the literature.<n>We propose a novel evaluation method that leverages fully homomorphic encryption.
  arXiv  Detail & Related papers  (2024-03-21T14:36:55Z)
• Robustness Threats of Differential Privacy [70.818129585404]
  We experimentally demonstrate that networks, trained with differential privacy, in some settings might be even more vulnerable in comparison to non-private versions. We study how the main ingredients of differentially private neural networks training, such as gradient clipping and noise addition, affect the robustness of the model.
  arXiv  Detail & Related papers  (2020-12-14T18:59:24Z)

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.