Related papers: Dropping Activation Outputs with Localized First-l…

This study investigates the risks of exposing confidential chemical structures when machine learning models trained on these structures are made publicly available. We use membership inference attacks, a common method to assess privacy that…

It is commonplace to produce application-specific models by fine-tuning large pre-trained models using a small bespoke dataset. The widespread availability of foundation model checkpoints on the web poses considerable risks, including the…

Federated learning (FL) allows the collaborative training of AI models without needing to share raw data. This capability makes it especially interesting for healthcare applications where patient and data privacy is of utmost concern.…

As network data has become increasingly prevalent, a substantial amount of attention has been paid to the privacy issue in publishing network data. One of the critical challenges for data publishers is to preserve the topological structures…

Collaborative inference in next-generation networks can enhance Artificial Intelligence (AI) applications, including autonomous driving, personal identification, and activity classification. This method involves a three-stage process: a)…

We develop a new method for regularising neural networks. We learn a probability distribution over the activations of all layers of the model and then insert imputed values into the network during training. We obtain a posterior for an…

Practitioners commonly download pretrained machine learning models from open repositories and finetune them to fit specific applications. We show that this practice introduces a new risk of privacy backdoors. By tampering with a pretrained…

Federated learning has emerged as a prominent privacy-preserving technique for leveraging large-scale distributed datasets by sharing gradients instead of raw data. However, recent studies indicate that private training data can still be…

Differentially private (DP) decentralized Federated Learning (FL) allows local users to collaborate without sharing their data with a central server. However, accurately quantifying the privacy budget of private FL algorithms is challenging…

Collaborative training of neural networks leverages distributed data by exchanging gradient information between different clients. Although training data entirely resides with the clients, recent work shows that training data can be…

Deep neural networks require large amounts of resources which makes them hard to use on resource constrained devices such as Internet-of-things devices. Offloading the computations to the cloud can circumvent these constraints but…

Federated learning (FL) as one of the novel branches of distributed machine learning (ML), develops global models through a private procedure without direct access to local datasets. However, access to model updates (e.g. gradient updates…

Local differential privacy (LDP) is a model where users send privatized data to an untrusted central server whose goal it to solve some data analysis task. In the non-interactive version of this model the protocol consists of a single round…

A deep learning model usually has to sacrifice some utilities when it acquires some other abilities or characteristics. Privacy preservation has such trade-off relationships with utilities. The loss disparity between various defense…

The Deep Leakage from Gradient (DLG) attack has emerged as a prevalent and highly effective method for extracting sensitive training data by inspecting exchanged gradients. This approach poses a substantial threat to the privacy of…

Local Differential Privacy (LDP) is the gold standard trust model for privacy-preserving machine learning by guaranteeing privacy at the data source. However, its application to image data has long been considered impractical due to the…

In the last decade, data-driven algorithms outperformed traditional optimization-based algorithms in many research areas, such as computer vision, natural language processing, etc. However, extensive data usages bring a new challenge or…

When training a machine learning model, it is standard procedure for the researcher to have full knowledge of both the data and model. However, this engenders a lack of trust between data owners and data scientists. Data owners are…

Deep learning-based face recognition (FR) systems pose significant privacy risks by tracking users without their consent. While adversarial attacks can protect privacy, they often produce visible artifacts compromising user experience. To…

A novel signaling design for secure transmission over two-user multiple-input multiple-output non-orthogonal multiple access channel using deep neural networks (DNNs) is proposed. The goal of the DNN is to form the covariance matrix of…