Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,742 papers · 148 categories

Trend · papers per month

152304455607 · Jun 202019922001200920172026
48 results for deep privacy

This study examines how model architecture affects deep learning model privacy.

problem Privacy concerns in deep learning models due to potential leakage of sensitive information.
method Investigation of CNNs and Transformers, focusing on activation layers, stem layers, LN layers, and attention modules.
result Transformers generally exhibit higher vulnerability to privacy attacks than CNNs.

Paper simplifies DP composition for adaptive privacy budgets, enabling better privacy and accuracy in deep learning.

problem Tension between efficiency and flexibility in DP composition theorems.
method Rényi Differential Privacy (RDP) for adaptive privacy budgets, proving simpler composition theorem with smaller constants.
result Practical DP composition for adaptive privacy budgets, enabling better privacy and accuracy in deep learning.

Paper evaluates and mitigates privacy risks in deep learning models.

problem Quantifying and defending against privacy attacks in deep learning.
method Quantitative evaluation of trade-offs, reformulating attacks, and proposing a novel SPN.
result Model accuracy improved by 5-20% while maintaining data privacy.

We detail a new framework for privacy preserving deep learning and discuss its assets. The framework puts a premium on ownership and secure processing of data and introduces a valuable representation based on chains of commands and tensors. This abstraction allows one to implement complex privacy preserving constructs …

2018-11-09abs ↗pdf ↗

Synthetic tabular data improves privacy while maintaining model performance.

problem Protecting privacy in synthetic data generation for machine learning.
method Deep generative models for tabular data, emphasizing privacy and model performance.
result Deep generative models enhance synthetic data generation for tabular datasets.

Normalization layers improve the accuracy of Differentially Private training of deep neural networks.

problem Reduced accuracy in deep neural networks with Differentially Private training.
method Proposed a novel method for integrating batch normalization with Differentially Private Stochastic Gradient Descent (DPSGD) without additional privacy loss.
result Training deeper networks with better utility-privacy trade-off is possible.

This paper improves deep learning models' accuracy with differential privacy using gradient encoding and denoising.

problem Deep learning models leak sensitive information about their training datasets.
method Gradient encoding to map gradients to a smaller vector space, and denoising for post-processing.
result Our technique achieves better model accuracy with differential privacy guarantees compared to state-of-the-art methods.

The paper investigates how data imbalance affects fairness and accuracy in differentially private deep learning.

problem Impact of data imbalance on fairness and accuracy in differentially private deep learning.
method Study the effects of different levels of imbalance in the data on the accuracy and fairness of decisions made by a model trained with differential privacy.
result Small imbalances and loose privacy guarantees can cause disparate impacts on model accuracy and fairness.

This paper introduces a novel approach to measuring privacy risks in deep computer vision models based on intermediate outputs.

problem The exposure of intermediate results in hidden layers of deep computer vision models poses significant privacy concerns.
method The approach leverages Degrees of Freedom (DoF) to evaluate the amount of information retained in each layer and combines this with the rank of the Jacobian matrix to assess sensitivity to input variations.
result The proposed framework provides deeper insights into privacy risks associated with intermediate representations without requiring adversarial attack simulations.

The paper proposes a fair and private decentralized deep learning framework.

problem Ensuring fairness and privacy in collaborative deep learning.
method A reputation system and differential privacy are used. FDPDDL framework is built with two stages: initialisation and update.
result FDPDDL achieves high fairness, comparable accuracy to centralised and distributed frameworks, and better accuracy than standalone.

Structured subsampling improves privacy in deep time series forecasting.

problem Incompatible privacy guarantees with time series forecasting.
method Structured subsampling of sequential data for privacy amplification.
result Structured subsampling enables training with strong privacy guarantees.

The remarkable development of deep learning in medicine and healthcare domain presents obvious privacy issues, when deep neural networks are built on users' personal and highly sensitive data, e.g., clinical records, user profiles, biomedical images, etc. However, only a few scientific studies on preserving privacy in …

2017-06-25abs ↗pdf ↗

AdaDPIGU improves privacy in deep learning by adaptively clipping and pruning gradients.

problem Privacy in deep learning models, especially in high-dimensional settings.
method Importance-based gradient updates, adaptive clipping, differentially private SGD.
result AdaDPIGU achieves high accuracy while maintaining privacy, outperforming non-private models.

DPlis improves privacy in deep learning models by smoothing loss functions.

problem Privacy leakage in deep learning models trained on private data and low model performance.
method DPlis constructs a smooth loss function to favor noise-resilient models.
result DPlis effectively boosts model quality and training stability under privacy constraints.

A new DP method for deep learning with faster convergence and better privacy.

problem Challenges in differentially private training of deep neural networks.
method Method of auxiliary coordinates with perturbed Taylor expansion for privacy.
result Empirically shows decent trained model quality with modest privacy budget.

Edgeworth Accountant calculates privacy loss under differential privacy compositions efficiently.

problem Efficiently computing overall privacy loss under composition of private algorithms.
method Analytical approach using ff-differential privacy framework and Edgeworth expansion.
result Non-asymptotic (ε,δ)(ε, δ)-differential privacy bounds with reduced computational cost.

Privacy-preserving GNNs for graph data with sensitive node data.

problem Privacy concerns in learning node representations for graphs with sensitive data.
method Developed a privacy-preserving GNN learning algorithm based on Local Differential Privacy (LDP). Proposed an LDP encoder, an unbiased rectifier, and a denoising mechanism (KProp).
result Our method maintains a satisfying level of accuracy with low privacy loss.

A new privacy-preserving deep learning scheme for asymmetrically collaborative machine learning.

problem Privacy and efficiency in collaborative machine learning across different data owners.
method Decomposes neural network steps for privacy-preserving training; novel protocol for information leakage.
result Efficient training with stable performance and significant speedup.

Machine learning techniques based on neural networks are achieving remarkable results in a wide variety of domains. Often, the training of models requires large, representative datasets, which may be crowdsourced and contain sensitive information. The models should not expose private information in these datasets. Addr…

2016-07-01abs ↗pdf ↗

This paper presents a method to train a public model with private data using GANs and differential privacy.

problem Privacy concerns in training deep learning models on sensitive data.
method A three-player learning framework with differential privacy protection.
result The proposed method achieves a balance between privacy and model accuracy.

Develops a new deep learning framework for privacy-preserving text representations.

problem Privacy concerns in deep learning frameworks requiring data pooling to a trusted server.
method Three modules: embedding, randomization, and classifier. Novel LDP protocol reduces privacy impact on accuracy.
result Framework delivers comparable or better performance than non-private and existing LDP protocols.

Machine learning models benefit from large and diverse datasets. Using such datasets, however, often requires trusting a centralized data aggregator. For sensitive applications like healthcare and finance this is undesirable as it could compromise patient privacy or divulge trade secrets. Recent advances in secure and …

2018-07-17abs ↗pdf ↗

Researchers found PP-GANs can hide sensitive data in sanitized images, undermining privacy checks.

problem Lack of formal proofs of privacy in PP-GANs for image sanitization.
method Subverted PP-GANs for facial expression recognition to hide sensitive data in sanitized images.
result It is possible to hide sensitive identification data in sanitized PP-GAN output images, even allowing reconstruction of entire input images.

Efficient framework for training machine learning models at edge without data movement.

problem Lack of privacy-preserving and computationally efficient methods for deep learning model training.
method Privacy preserving FedCollabNN framework for federated learning.
result Framework is computationally efficient and robust against adversarial attacks.

Privacy can be achieved without cost in overparameterized models.

problem Understanding the performance cost of differentially private gradient descent in overparameterized settings.
method Random features model with quadratic loss.
result Privacy can be obtained for free in the overparameterized regime, not dependent on privacy parameter ε.

Paper proposes scalable privacy-preserving DNN for industrial applications.

problem Data isolation and scalability issues in deep neural networks.
method Split computation graph into private and neutral server parts; use cryptographic techniques for private data.
result Demonstrates practicality of the proposed scalable privacy-preserving DNN.

This paper quantifies privacy-robustness and generalization-robustness trade-offs in adversarial training.

problem Privacy and generalization issues in adversarial training.
method Defines robustified intensity and empirical robustified intensity to measure robustness, proving differential privacy and generalization bounds.
result Proves adversarial training is (ε,δ)(\varepsilon, δ)-differentially private and provides generalization bounds.

New DP mechanism SWAG-PPM improves privacy in deep learning models.

problem Differential privacy struggles with real-world distributions, especially imbalanced data.
method SWAG-PPM uses a pseudo posterior distribution to downweight high-risk records.
result SWAG-PPM outperforms DP-SGD with similar privacy budget and modest utility degradation.

Paper tightens privacy and generalization bounds for iterative learning.

problem Balancing privacy and generalization in iterative learning algorithms.
method Established alignment between generalization and privacy, derived composition theorems for iterative algorithms.
result Generalization bounds for iterative learning algorithms are strictly tighter than existing works.

New methods speed up training of differentially private deep learning models.

problem Training differentially private deep learning models is slower than non-private models.
method Derive and implement new per-example gradient clipping methods compatible with auto-differentiation.
result Significant training speed-ups (54x - 94x) for various models and architectures.

DPNR preserves privacy of text representations using differential privacy.

problem Privacy leakage in deep learning text representations.
method DPNR uses Differential Privacy to provide formal privacy guarantees and dropout masking for enhanced privacy.
result DPNR reduces privacy leakage without significantly sacrificing main task performance.

In this paper, we address the problem of data reconstruction from privacy-protected templates, based on recent concept of sparse ternary coding with ambiguization (STCA). The STCA is a generalization of randomization techniques which includes random projections, lossy quantization, and addition of ambiguization noise t…

2019-05-08abs ↗pdf ↗

Classifies privacy policy segments for better user understanding.

problem Difficulty in understanding privacy policies due to legal jargon.
method Uses machine learning and deep learning techniques to classify privacy policy segments.
result Identifies data practices in privacy policies for better user comprehension.