Related papers: Uncertainty-Autoencoder-Based Privacy and Utility …
Privacy-preserving data release mechanisms aim to simultaneously minimize information-leakage with respect to sensitive data and distortion with respect to useful data. Dependencies between sensitive and useful data results in a…
Federated Learning (FL) has gained prominence in machine learning applications across critical domains by enabling collaborative model training without centralized data aggregation. However, FL frameworks that protect privacy often…
Variational Autoencoders for multimodal data hold promise for many tasks in data analysis, such as representation learning, conditional generation, and imputation. Current architectures either share the encoder output, decoder input, or…
A critical concern in data-driven processes is to build models whose outcomes do not discriminate against some demographic groups, including gender, ethnicity, or age. To ensure non-discrimination in learning tasks, knowledge of the group…
We propose using an adversarial autoencoder (AAE) to replace generative adversarial network (GAN) in the private aggregation of teacher ensembles (PATE), a solution for ensuring differential privacy in speech applications. The AAE…
How can we learn a representation with high predictive power while preserving user privacy? We present an adversarial representation learning method for sanitizing sensitive content from the learned representation. Specifically, we…
We investigate the problem of learning representations that are invariant to certain nuisance or sensitive factors of variation in the data while retaining as much of the remaining information as possible. Our model is based on a…
Learning-augmented data structures use predicted frequency estimates to retrieve frequently occurring database elements faster than standard data structures. Recent work has developed data structures that optimally exploit these frequency…
The widespread deployment of Artificial Intelligence (AI) across government and private industries brings both advancements and heightened privacy and security concerns. Article 17 of the General Data Protection Regulation (GDPR) mandates…
Confidentiality for business data is an understudied area of disclosure avoidance, where legacy methods struggle to provide acceptable results. Standard formal privacy techniques for person-level data, like differential privacy, are…
The problem of estimating event truths from conflicting agent opinions in a social network is investigated. An autoencoder learns the complex relationships between event truths, agent reliabilities and agent observations. A Bayesian network…
A critical concern in data-driven decision making is to build models whose outcomes do not discriminate against some demographic groups, including gender, ethnicity, or age. To ensure non-discrimination in learning tasks, knowledge of the…
Open set domain adaptation refers to the scenario that the target domain contains categories that do not exist in the source domain. It is a more common situation in the reality compared with the typical closed set domain adaptation where…
In the realm of healthcare where decentralized facilities are prevalent, machine learning faces two major challenges concerning the protection of data and models. The data-level challenge concerns the data privacy leakage when centralizing…
Machine learning models have shone in a variety of domains and attracted increasing attention from both the security and the privacy communities. One important yet worrying question is: Will training models under the differential privacy…
Autoencoders (AE) have recently been widely employed to approach the novelty detection problem. Trained only on the normal data, the AE is expected to reconstruct the normal data effectively while fail to regenerate the anomalous data,…
A privacy-utility tradeoff is developed for an arbitrary set of finite-alphabet source distributions. Privacy is quantified using differential privacy (DP), and utility is quantified using expected Hamming distortion maximized over the set…
Data is used widely by service providers as input to inference systems to perform decision making for authorized tasks. The raw data however allows a service provider to infer other sensitive information it has not been authorized for. We…
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…
Deep ensemble learning has been shown to improve accuracy by training multiple neural networks and averaging their outputs. Ensemble learning has also been suggested to defend against membership inference attacks that undermine privacy. In…