相关论文: Uncertainty-Autoencoder-Based Privacy and Utility …

Deep neural networks are increasingly deployed for scene analytics, including to evaluate the attention and reaction of people exposed to out-of-home advertisements. However, the features extracted by a deep neural network that was trained…

Privacy-preserving machine learning in data-sharing processes is an ever-critical task that enables collaborative training of Machine Learning (ML) models without the need to share the original data sources. It is especially relevant when…

Crowdsourced data used in machine learning services might carry sensitive information about attributes that users do not want to share. Various methods have been proposed to minimize the potential information leakage of sensitive attributes…

We introduce a deep learning framework able to deal with strong privacy constraints. Based on collaborative learning, differential privacy and homomorphic encryption, the proposed approach advances state-of-the-art of private deep learning…

Recommendation is one of the critical applications that helps users find information relevant to their interests. However, a malicious attacker can infer users' private information via recommendations. Prior work obfuscates user-item data…

Due to the recent popularity of online social networks, coupled with people's propensity to disclose personal information in an effort to achieve certain gratifications, the problem of navigating the tradeoff between privacy and utility…

Deep neural networks do not discriminate between spurious and causal patterns, and will only learn the most predictive ones while ignoring the others. This shortcut learning behaviour is detrimental to a network's ability to generalize to…

Each agent in a network makes a local observation that is linearly related to a set of public and private parameters. The agents send their observations to a fusion center to allow it to estimate the public parameters. To prevent leakage of…

Malicious adversaries can attack machine learning models to infer sensitive information or damage the system by launching a series of evasion attacks. Although various work addresses privacy and security concerns, they focus on individual…

We propose a general learning framework for the protection mechanisms that protects privacy via distorting model parameters, which facilitates the trade-off between privacy and utility. The algorithm is applicable to arbitrary privacy…

In this paper we investigate the vulnerability that facial recognition systems present to adversarial examples by introducing a new methodology from the attacker perspective. The technique is based on the use of the autoencoder latent…

It has been a significant challenge to portray intraclass disparity precisely in the area of activity recognition, as it requires a robust representation of the correlation between subject-specific variation for each activity class. In this…

Collaborative filtering algorithms capture underlying consumption patterns, including the ones specific to particular demographics or protected information of users, e.g. gender, race, and location. These encoded biases can influence the…

Ensuring differential privacy of models learned from sensitive user data is an important goal that has been studied extensively in recent years. It is now known that for some basic learning problems, especially those involving…

It is often necessary to disclose training data to the public domain, while protecting privacy of certain sensitive labels. We use information theoretic measures to develop such privacy preserving data disclosure mechanisms. Our mechanism…

Classifiers in supervised learning have various security and privacy issues, e.g., 1) data poisoning attacks, backdoor attacks, and adversarial examples on the security side as well as 2) inference attacks and the right to be forgotten for…

Over the last decade, the use of Automatic Speaker Verification (ASV) systems has become increasingly widespread in response to the growing need for secure and efficient identity verification methods. The voice data encompasses a wealth of…

We address the challenging open problem of learning an effective latent space for symbolic music data in generative music modeling. We focus on leveraging adversarial regularization as a flexible and natural mean to imbue variational…

Preserving the individuals' privacy in sharing spatial-temporal datasets is critical to prevent re-identification attacks based on unique trajectories. Existing privacy techniques tend to propose ideal privacy-utility tradeoffs, however,…

Face images are rich data items that are useful and can easily be collected in many applications, such as in 1-to-1 face verification tasks in the domain of security and surveillance systems. Multiple methods have been proposed to protect…