CLOAK: Contrastive Guidance for Latent Diffusion-Based Data Obfuscation

• URL: http://arxiv.org/abs/2512.12086v1
• Date: Fri, 12 Dec 2025 23:30:43 GMT
• Title: CLOAK: Contrastive Guidance for Latent Diffusion-Based Data Obfuscation
• Abstract summary: Data obfuscation is a promising technique for mitigating attribute inference attacks by semi-trusted parties with access to time-series data emitted by sensors.<n>We propose Cloak, a novel data obfuscation framework based on latent diffusion models.<n>In contrast to prior work, we employ contrastive learning to extract disentangled representations, which guide the latent diffusion process to retain useful information while concealing private information.
• Score: 6.2048266436284605
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Data obfuscation is a promising technique for mitigating attribute inference attacks by semi-trusted parties with access to time-series data emitted by sensors. Recent advances leverage conditional generative models together with adversarial training or mutual information-based regularization to balance data privacy and utility. However, these methods often require modifying the downstream task, struggle to achieve a satisfactory privacy-utility trade-off, or are computationally intensive, making them impractical for deployment on resource-constrained mobile IoT devices. We propose Cloak, a novel data obfuscation framework based on latent diffusion models. In contrast to prior work, we employ contrastive learning to extract disentangled representations, which guide the latent diffusion process to retain useful information while concealing private information. This approach enables users with diverse privacy needs to navigate the privacy-utility trade-off with minimal retraining. Extensive experiments on four public time-series datasets, spanning multiple sensing modalities, and a dataset of facial images demonstrate that Cloak consistently outperforms state-of-the-art obfuscation techniques and is well-suited for deployment in resource-constrained settings.

Related papers

• Phantoms and Disclosures: a Causal Framework for Auditing Synthetic Data [56.86147283213652]
  We present a customizable empirical auditing framework designed to detect and explain data disclosures.<n>Our framework introduces a mechanism to distinguish between "true disclosures"-where the system directly reproduces a user's information-and "phantom disclosures"-where the system incidentally generates a user's data.
  arXiv  Detail & Related papers  (2026-06-15T16:54:02Z)
• Defense Against Prompt Inversion Attacks: An Information-Theoretic Approach for LLM Collaborative Inference [5.218013327284395]
  Collaborative edge-cloud inference enables resource-constrained devices to leverage large language models (LLMs) by offloading partial computation to cloud servers.<n> transmitting intermediate activations exposes sensitive user prompts to prompt inversion attacks.<n>We propose an information-theoretic defense framework for prompt inversion in collaborative LLM inference.
  arXiv  Detail & Related papers  (2026-06-10T02:36:26Z)
• Deep Leakage with Generative Flow Matching Denoiser [54.05993847488204]
  We introduce a new deep leakage (DL) attack that integrates a generative Flow Matching (FM) prior into the reconstruction process.<n>Our approach consistently outperforms state-of-the-art attacks across pixel-level, perceptual, and feature-based similarity metrics.
  arXiv  Detail & Related papers  (2026-01-21T14:51:01Z)
• Continuous-time Discrete-space Diffusion Model for Recommendation [25.432419904462694]
  CDRec is a novel Continuous-time Discrete-space Diffusion Recommendation framework.<n>It is superior in both recommendation accuracy and computational efficiency.<n>Experiments on real-world datasets demonstrate CDRec's superior performance in both recommendation accuracy and computational efficiency.
  arXiv  Detail & Related papers  (2025-11-15T09:06:57Z)
• Improving Noise Efficiency in Privacy-preserving Dataset Distillation [59.57846442477106]
  We introduce a novel framework that decouples sampling from optimization for better convergence and improves signal quality.<n>On CIFAR-10, our method achieves a textbf10.0% improvement with 50 images per class and textbf8.3% increase with just textbfone-fifth the distilled set size of previous state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-08-03T13:15:52Z)
• PrivDiffuser: Privacy-Guided Diffusion Model for Data Obfuscation in Sensor Networks [4.91258288207688]
  Sensor data collected by Internet of Things (IoT) devices can reveal sensitive personal information about individuals.<n>Data obfuscation empowered by generative models is a promising approach to generate synthetic data.<n>We propose PrivDiffuser, a novel data obfuscation technique that achieves a superior trade-off between data utility and privacy.
  arXiv  Detail & Related papers  (2024-12-19T03:47:12Z)
• Pseudo-Probability Unlearning: Towards Efficient and Privacy-Preserving Machine Unlearning [59.29849532966454]
  We propose PseudoProbability Unlearning (PPU), a novel method that enables models to forget data to adhere to privacy-preserving manner. Our method achieves over 20% improvements in forgetting error compared to the state-of-the-art.
  arXiv  Detail & Related papers  (2024-11-04T21:27:06Z)
• Ungeneralizable Examples [70.76487163068109]
  Current approaches to creating unlearnable data involve incorporating small, specially designed noises. We extend the concept of unlearnable data to conditional data learnability and introduce textbfUntextbfGeneralizable textbfExamples (UGEs) UGEs exhibit learnability for authorized users while maintaining unlearnability for potential hackers.
  arXiv  Detail & Related papers  (2024-04-22T09:29:14Z)
• Bistochastically private release of data streams with zero delay [0.0]
  We propose a protocol for the anonymization of data streams that achieves zero delay while exhibiting formal privacy guarantees. We show that it is feasible to achieve an atomic processing of individuals entering a stream, in-stead of proceeding by batches.
  arXiv  Detail & Related papers  (2024-02-25T14:18:14Z)
• The Devil's Advocate: Shattering the Illusion of Unexploitable Data using Diffusion Models [14.018862290487617]
  We show that a carefully designed denoising process can counteract the data-protecting perturbations. Our approach, called AVATAR, delivers state-of-the-art performance against a suite of recent availability attacks.
  arXiv  Detail & Related papers  (2023-03-15T10:20:49Z)
• Differentially-Private Data Synthetisation for Efficient Re-Identification Risk Control [3.8811062755861956]
  $epsilon$-PrivateSMOTE is a technique for safeguarding against re-identification and linkage attacks. Our proposal combines synthetic data generation via noise-induced adversarial with differential privacy principles to obfuscate high-risk cases.
  arXiv  Detail & Related papers  (2022-12-01T13:20:37Z)
• Private Set Generation with Discriminative Information [63.851085173614]
  Differentially private data generation is a promising solution to the data privacy challenge. Existing private generative models are struggling with the utility of synthetic samples. We introduce a simple yet effective method that greatly improves the sample utility of state-of-the-art approaches.
  arXiv  Detail & Related papers  (2022-11-07T10:02:55Z)
• Over-the-Air Federated Learning with Privacy Protection via Correlated Additive Perturbations [57.20885629270732]
  We consider privacy aspects of wireless federated learning with Over-the-Air (OtA) transmission of gradient updates from multiple users/agents to an edge server. Traditional perturbation-based methods provide privacy protection while sacrificing the training accuracy. In this work, we aim at minimizing privacy leakage to the adversary and the degradation of model accuracy at the edge server.
  arXiv  Detail & Related papers  (2022-10-05T13:13:35Z)
• Differentially Private Federated Learning with Laplacian Smoothing [72.85272874099644]
  Federated learning aims to protect data privacy by collaboratively learning a model without sharing private data among users. An adversary may still be able to infer the private training data by attacking the released model. Differential privacy provides a statistical protection against such attacks at the price of significantly degrading the accuracy or utility of the trained models.
  arXiv  Detail & Related papers  (2020-05-01T04:28:38Z)

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.