相关论文: Training Data Reconstruction: Privacy due to Uncer…

Unlearnable examples are proposed to prevent third parties from exploiting unauthorized data, which generates unlearnable examples by adding imperceptible perturbations to public publishing data. These unlearnable examples proficiently…

Statistical methods protecting sensitive information or the identity of the data owner have become critical to ensure privacy of individuals as well as of organizations. This paper investigates anonymization methods based on representation…

Automated machine vision pipelines do not need the exact visual content to perform their tasks. Therefore, there is a potential to remove private information from the data without significantly affecting the machine vision accuracy. We…

Uncertainty calibration is crucial for various machine learning applications, yet it remains challenging. Many models exhibit hallucinations - confident yet inaccurate responses - due to miscalibrated confidence. Here, we show that the…

Understanding whether deep neural networks are effectively optimized remains challenging, as training occurs in highly nonconvex landscapes and standard metrics provide limited visibility into layer-wise learning quality. This challenge is…

Machine unlearning is a promising paradigm for removing unwanted data samples from a trained model, towards ensuring compliance with privacy regulations and limiting harmful biases. Although unlearning has been shown in, e.g.,…

Large-scale deep learning models are known to memorize parts of the training set. In machine learning theory, memorization is often framed as interpolation or label fitting, and classical results show that this can be achieved when the…

We study a privacy-preserving data-sharing setting where a privatizer transforms private data into a sanitized version observed by an authorized reconstructor and two unauthorized adversaries, each with access to side information correlated…

In this effort we propose a novel approach for reconstructing multivariate functions from training data, by identifying both a suitable network architecture and an initialization using polynomial-based approximations. Training deep neural…

Massive data exist among user local platforms that usually cannot support deep neural network (DNN) training due to computation and storage resource constraints. Cloud-based training schemes provide beneficial services but suffer from…

This paper proposes a straightforward and cost-effective approach to assess whether a deep neural network (DNN) relies on the primary concepts of training samples or simply learns discriminative, yet simple and irrelevant features that can…

Deep Neural networks forget previously learnt tasks when they are faced with learning new tasks. This is called catastrophic forgetting. Rehearsing the neural network with the training data of the previous task can protect the network from…

We introduce an optimization-based reconstruction attack capable of completely or near-completely reconstructing a dataset utilized for training a random forest. Notably, our approach relies solely on information readily available in…

In this paper, we study a simple and generic framework to tackle the problem of learning model parameters when a fraction of the training samples are corrupted. We first make a simple observation: in a variety of such settings, the…

Machine learning offers attractive solutions to challenging image processing tasks. Tedious development and parametrization of algorithmic solutions can be replaced by training a convolutional neural network or a random forest with a high…

Input space reconstruction is an attractive representation learning paradigm. Despite interpretability of the reconstruction and generation, we identify a misalignment between learning by reconstruction, and learning for perception. We show…

Deep learning model developers often use cloud GPU resources to experiment with large data and models that need expensive setups. However, this practice raises privacy concerns. Adversaries may be interested in: 1) personally identifiable…

Privacy attacks on machine learning models aim to identify the data that is used to train such models. Such attacks, traditionally, are studied on static models that are trained once and are accessible by the adversary. Motivated to meet…

This paper aims to improve privacy-preserving visual recognition, an increasingly demanded feature in smart camera applications, by formulating a unique adversarial training framework. The proposed framework explicitly learns a degradation…

Machine unlearning, an emerging research topic focusing on compliance with data privacy regulations, enables trained models to remove the information learned from specific data. While many existing methods indirectly address this issue by…