Related papers: Label Leakage and Protection in Two-party Split Le…
Secure multiparty computation (MPC) allows data owners to train machine learning models on combined data while keeping the underlying training data private. The MPC threat model either considers an adversary who passively corrupts some…
Data privacy and decentralised data collection has become more and more popular in recent years. In order to solve issues with privacy, communication bandwidth and learning from spatio-temporal data, we will propose two efficient models…
Partial-label learning (PLL) is a typical weakly supervised learning problem, where each training instance is equipped with a set of candidate labels among which only one is the true label. Most existing methods elaborately designed…
Split Learning (SL) and Federated Learning (FL) are two prominent distributed collaborative learning techniques that maintain data privacy by allowing clients to never share their private data with other clients and servers, and fined…
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.…
Leakage of data from publicly available Machine Learning (ML) models is an area of growing significance as commercial and government applications of ML can draw on multiple sources of data, potentially including users' and clients'…
Deep learning has transformed AI applications but faces critical security challenges, including adversarial attacks, data poisoning, model theft, and privacy leakage. This survey examines these vulnerabilities, detailing their mechanisms…
Federated Learning (FL) is a distributed learning paradigm that enhances users privacy by eliminating the need for clients to share raw, private data with the server. Despite the success, recent studies expose the vulnerability of FL to…
In this paper we consider the setting where machine learning models are retrained on updated datasets in order to incorporate the most up-to-date information or reflect distribution shifts. We investigate whether one can infer information…
Split learning enables efficient and privacy-aware training of a deep neural network by splitting a neural network so that the clients (data holders) compute the first layers and only share the intermediate output with the central…
Large language models (LLMs) demonstrate remarkable capabilities across various tasks. However, their deployment introduces significant risks related to intellectual property. In this context, we focus on model stealing attacks, where…
Federated learning has gained great attention recently as a privacy-enhancing tool to jointly train a machine learning model by multiple parties. As a sub-category, vertical federated learning (vFL) focuses on the scenario where features…
Many machine learning systems rely on data collected in the wild from untrusted sources, exposing the learning algorithms to data poisoning. Attackers can inject malicious data in the training dataset to subvert the learning process,…
We consider a collaborative learning scenario in which multiple data-owners wish to jointly train a logistic regression model, while keeping their individual datasets private from the other parties. We propose COPML, a fully-decentralized…
We introduce Split Unlearning, a novel machine unlearning technology designed for Split Learning (SL), enabling the first-ever implementation of Sharded, Isolated, Sliced, and Aggregated (SISA) unlearning in SL frameworks. Particularly, the…
Federated learning is emerging as a machine learning technique that trains a model across multiple decentralized parties. It is renowned for preserving privacy as the data never leaves the computational devices, and recent approaches…
The growing importance of massive datasets used for deep learning makes robustness to label noise a critical property for classifiers to have. Sources of label noise include automatic labeling, non-expert labeling, and label corruption by…
Label distribution learning (LDL) is an effective method to predict the label description degree (a.k.a. label distribution) of a sample. However, annotating label distribution (LD) for training samples is extremely costly. So recent…
In this work, we propose information laundering, a novel framework for enhancing model privacy. Unlike data privacy that concerns the protection of raw data information, model privacy aims to protect an already-learned model that is to be…
Language Models (LMs) have been shown to leak information about training data through sentence-level membership inference and reconstruction attacks. Understanding the risk of LMs leaking Personally Identifiable Information (PII) has…