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.

168,695 papers · 148 categories

Trend · papers per month

72144215287 · Jun 202019922001200920172026
48 results for private images

Paper analyzes InstaHide's security, recovering all private images with provable guarantee.

problem Protecting privacy of training data in neural networks.
method Unified framework to understand and analyze attacks on InstaHide, presenting a new algorithm to recover all private images with provable guarantee.
result InstaHide is computationally secure but not information-theoretically secure when mixing two private images.

Improved image generation with private data using perceptual features.

problem Difficulty in training generative models with differential privacy.
method Use pre-trained perceptual features to learn private data distribution.
result Generative models can generate high-quality images with low privacy budget (ϵ2\epsilon \approx 2).

Differentially private GANs improve image privacy without significant quality loss.

problem Anonymizing image data sets while maintaining image quality.
method Training GANs with differential privacy on MNIST, analyzing privacy-utility trade-offs and explaining optimization methods.
result An increasing privacy budget adds little to generated image quality, revealing a saturated training regime.

DP-RandP improves privacy-utility tradeoff in DP-SGD by learning priors from random processes.

problem Improving the performance of differentially private stochastic gradient descent (DP-SGD) on private data.
method A three-phase approach that learns priors from images generated by random processes and transfers these priors to private data.
result New state-of-the-art accuracy on CIFAR10, CIFAR100, MedMNIST, and ImageNet for various privacy budgets.

New attack recovers user-level information from large batch images.

problem Recovering private information from user-level gradients in distributed learning.
method Proposes a gradient inversion attack using a denoising diffusion model as a prior.
result Demonstrates recovery of realistic facial images and private attributes.

New insights into image compression trade-offs with private randomness.

problem Trade-off between compression rate and perceptual quality in image compression.
method Characterization of rate-distortion trade-off with private randomness under different realism constraints.
result Encoder private randomness is not useful if compression rate is below source entropy, even with limited common and decoder private randomness.

Improved DP-SGD on large models achieves high accuracy on image classification tasks.

problem Differentially private image classification often degrades performance.
method Careful hyper-parameter tuning and signal propagation techniques.
result Achieved 81.4% top-1 accuracy on CIFAR-10 under (8, 10^{-5})-DP.

Paper explores how non-neural simulators can enhance DP synthetic data generation.

problem Generating differentially private synthetic data without access to foundation models.
method Private Evolution (PE) framework using inference APIs and simulators.
result Sim-PE framework improves downstream classification accuracy and FID scores.

Adversarial examples are intentionally perturbed images that mislead classifiers. These images can, however, be easily detected using denoising algorithms, when high-frequency spatial perturbations are used, or can be noticed by humans, when perturbations are large. In this paper, we propose EdgeFool, an adversarial im…

2019-10-27abs ↗pdf ↗

Few-shot DP image classification models need more data as privacy increases.

problem Few-shot DP image classification challenges in personalization and federated learning.
method Exhaustive experiments on various parameters affecting few-shot DP accuracy and vulnerability.
result Increasing shots per class is necessary for DP accuracy as privacy increases.

PASS protects private attributes by stochastically substituting data.

problem Protecting private attributes in ML services while maintaining data utility.
method PASS uses stochastic data substitution with a novel loss function derived from information theory.
result PASS effectively protects private attributes across various datasets.

Private training and synthetic data generation using DP clustering.

problem Protecting sensitive data in deep neural networks training.
method Approximate input dataset with privately generated synthetic dataset using DP clustering.
result Simple two-layer neural network achieves SOTA classification accuracy on standard benchmark datasets.

AdaDPS uses side information to improve private adaptive optimization.

problem Private adaptive optimization methods degrade when training with differential privacy.
method AdaDPS uses non-sensitive side information to precondition gradients.
result AdaDPS reduces the amount of noise needed for similar privacy guarantees, improving optimization performance.

Hermite polynomials improve private data generation by reducing feature count.

problem Infinite-dimensional features in kernel mean embedding are impractical for private data generation.
method Replace random features with Hermite polynomial features, leveraging their ordered nature.
result Hermite polynomial features yield a more accurate approximation of kernel mean embedding with fewer features.

This work proposes a novel privacy-preserving method for synthetic replacement of sensitive data.

problem Privacy-preserving transformations of sensitive data.
method Adversarial representation learning for synthetic replacement of private attributes.
result Our method provides stronger privacy and better utility than previous methods.

Multi-modal data collections, such as corpora of paired images and text snippets, require analysis methods beyond single-view component and topic models. For continuous observations the current dominant approach is based on extensions of canonical correlation analysis, factorizing the variation into components shared b…

2012-10-16abs ↗pdf ↗

We present a framework to learn privacy-preserving encodings of images that inhibit inference of chosen private attributes, while allowing recovery of other desirable information. Rather than simply inhibiting a given fixed pre-trained estimator, our goal is that an estimator be unable to learn to accurately predict th…

2018-02-14abs ↗pdf ↗

Interpretable predictions, where it is clear why a machine learning model has made a particular decision, can compromise privacy by revealing the characteristics of individual data points. This raises the central question addressed in this paper: Can models be interpretable without compromising privacy? For complex big…

2019-06-05abs ↗pdf ↗

A new mechanism for differentially private Fréchet mean on SPD matrices.

problem Privacy-preserving statistical summaries for SPD matrices.
method Tangent Gaussian mechanism for log-Euclidean metric.
result Significantly better utility and computational efficiency.

To improve real-world applications of machine learning, experienced modelers develop intuition about their datasets, their models, and how the two interact. Manual inspection of raw data - of representative samples, of outliers, of misclassifications - is an essential tool in a) identifying and fixing problems in the d…

2019-11-15abs ↗pdf ↗

Generative Adversarial Networks (GAN) have shown great promise in tasks like synthetic image generation, image inpainting, style transfer, and anomaly detection. However, generating discrete data is a challenge. This work presents an adversarial training based correlated discrete data (CDD) generation model. It also de…

2018-04-03abs ↗pdf ↗

Private method measures nonlinear correlations between data hosted across two entities.

problem Measuring nonlinear correlations between sensitive data hosted across multiple parties while preserving privacy.
method Differentially private estimator of distance correlation.
result First private estimator of nonlinear correlations in a multi-party setup.

We present and evaluate Deep Private-Feature Extractor (DPFE), a deep model which is trained and evaluated based on information theoretic constraints. Using the selective exchange of information between a user's device and a service provider, DPFE enables the user to prevent certain sensitive information from being sha…

2018-02-09abs ↗pdf ↗

This paper benchmarks privacy-preserving machine learning on medical images.

problem Ensuring privacy in medical image analysis while maintaining model accuracy.
method Comparing Local-DP and DP-SGD for differential privacy in medical imagery.
result Theoretical privacy guarantees do not fully align with real-world performance.

Generative Adversarial Networks (GANs) are one of the well-known models to generate synthetic data including images, especially for research communities that cannot use original sensitive datasets because they are not publicly accessible. One of the main challenges in this area is to preserve the privacy of individuals…

2020-01-27abs ↗pdf ↗

Near-optimal private tests for simple and MLR hypotheses developed under Gaussian differential privacy.

problem Developing private tests for simple and MLR hypotheses under Gaussian differential privacy.
method A private mean estimator with data-driven clamping bounds, constructing private test statistics.
result Private tests achieve the same asymptotic relative efficiency as non-private most powerful tests.

Public pretraining improves private model training even in extreme distribution shift scenarios.

problem Improving private model training accuracy in settings with large distribution shift.
method Empirical evaluation and theoretical explanation of public representations improving private training accuracy.
result Public representations can improve private training accuracy by up to 67% over private training from scratch in settings with large distribution shift.

Widely-used public benchmarks are of huge importance to computer vision and machine learning research, especially with the computational resources required to reproduce state of the art results quickly becoming untenable. In medical image computing, the wide variety of image modalities and problem formulations yields a…

2019-08-12abs ↗pdf ↗

Private learning of Gaussian Mixture Models without boundedness assumptions.

problem Private estimation of parameters of Gaussian Mixture Models with unbounded components.
method Reduction to non-private problem, blackbox privatization, Moitra and Valiant's algorithm.
result First sample complexity upper bound and polynomial time algorithm for privately learning GMMs.

Parameter-transfer is a well-known and versatile approach for meta-learning, with applications including few-shot learning, federated learning, and reinforcement learning. However, parameter-transfer algorithms often require sharing models that have been trained on the samples from specific tasks, thus leaving the task…

2019-09-12abs ↗pdf ↗

A new method for privacy-preserving data distillation using wavelet features from ScatterNet.

problem Privacy-preserving data distillation for small datasets.
method Differentially private kernel inducing points using wavelet features from ScatterNet.
result Achieves privacy-preserving data distillation with manageable computational cost.