Related papers: Matrix Sketching for Secure Collaborative Machine …
Decentralized Gradient Descent (D-GD) allows a set of users to perform collaborative learning without sharing their data by iteratively averaging local model updates with their neighbors in a network graph. The absence of direct…
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…
This paper presents a holistic approach to gradient leakage resilient distributed Stochastic Gradient Descent (SGD). First, we analyze two types of strategies for privacy-enhanced federated learning: (i) gradient pruning with random…
Privacy-preserving machine learning enables the training of models on decentralized datasets without the need to reveal the data, both on horizontal and vertically partitioned data. However, it relies on specialized techniques and…
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…
The uses of Machine Learning (ML) in detection of network attacks have been effective when designed and evaluated in a single organisation. However, it has been very challenging to design an ML-based detection system by utilising…
Modern deep learning techniques focus on extracting intricate information from data to achieve accurate predictions. However, the training datasets may be crowdsourced and include sensitive information, such as personal contact details,…
Growing concerns surrounding AI safety and data privacy have driven the development of Machine Unlearning as a potential solution. However, current machine unlearning algorithms are designed to complement the offline training paradigm. The…
Differential privacy (DP) is the prevailing technique for protecting user data in machine learning models. However, deficits to this framework include a lack of clarity for selecting the privacy budget $\epsilon$ and a lack of…
Cascades are a common type of machine learning systems in which a large, remote model can be queried if a local model is not able to accurately label a user's data by itself. Serving stacks for large language models (LLMs) increasingly use…
Federated learning (FL) is a new paradigm that enables many clients to jointly train a machine learning (ML) model under the orchestration of a parameter server while keeping the local data not being exposed to any third party. However, the…
Model stealing attacks have become a serious concern for deep learning models, where an attacker can steal a trained model by querying its black-box API. This can lead to intellectual property theft and other security and privacy risks. The…
The most important characteristic of a Quantum Key Distribution (QKD) protocol is its security against third-party attacks, and the potential countermeasures available. While new types of attacks are regularly developed in the literature,…
Federated learning is a promising distributed learning paradigm that enables collaborative model training without exposing local client data, thereby protecting data privacy. However, it also brings new threats and challenges. The…
Meta-learning involves multiple learners, each dedicated to specific tasks, collaborating in a data-constrained setting. In current meta-learning methods, task learners locally learn models from sensitive data, termed support sets. These…
Differential privacy (DP) provides a formal privacy guarantee that prevents adversaries with access to machine learning models from extracting information about individual training points. Differentially private stochastic gradient descent…
Membership inference attacks (MIAs) are currently considered one of the main privacy attack strategies, and their defense mechanisms have also been extensively explored. However, there is still a gap between the existing defense approaches…
Distributed collaborative learning (DCL) paradigms enable building joint machine learning models from distrusting multi-party participants. Data confidentiality is guaranteed by retaining private training data on each participant's local…
Contrastive learning is widely used for recommendation model learning, where selecting representative and informative negative samples is critical. Existing methods usually focus on centralized data, where abundant and high-quality negative…
Federated learning is a distributed learning technique that allows training a global model with the participation of different data owners without the need to share raw data. This architecture is orchestrated by a central server that…