Related papers: Modelling and Quantifying Membership Information L…
In machine learning, curation is used to select the most valuable data for improving both model accuracy and computational efficiency. Recently, curation has also been explored as a solution for private machine learning: rather than…
Neural Network (Deep Learning) is a modern model in Artificial Intelligence and it has been exploited in Survival Analysis. Although several improvements have been shown by previous works, training an excellent deep learning model requires…
Federated learning is a decentralized machine learning approach where clients train models locally and share model updates to develop a global model. This enables low-resource devices to collaboratively build a high-quality model without…
Despite machine learning models being widely used today, the relationship between a model and its training dataset is not well understood. We explore correlation inference attacks, whether and when a model leaks information about the…
Distributed machine learning has been widely used in recent years to tackle the large and complex dataset problem. Therewith, the security of distributed learning has also drawn increasing attentions from both academia and industry. In this…
With the development of machine learning techniques, the attention of research has been moved from single-modal learning to multi-modal learning, as real-world data exist in the form of different modalities. However, multi-modal models…
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…
Membership inference attacks aim to infer whether a data record has been used to train a target model by observing its predictions. In sensitive domains such as healthcare, this can constitute a severe privacy violation. In this work we…
Natural language processing models have experienced a significant upsurge in recent years, with numerous applications being built upon them. Many of these applications require fine-tuning generic base models on customized, proprietary…
As large language models (LLMs) become progressively more embedded in clinical decision-support, documentation, and patient-information systems, ensuring their privacy and trustworthiness has emerged as an imperative challenge for the…
With the rapid advancement of deep learning technology, pre-trained encoder models have demonstrated exceptional feature extraction capabilities, playing a pivotal role in the research and application of deep learning. However, their…
Inference attacks against Machine Learning (ML) models allow adversaries to learn sensitive information about training data, model parameters, etc. While researchers have studied, in depth, several kinds of attacks, they have done so in…
With the growing emphasis on users' privacy, federated learning has become more and more popular. Many architectures have been raised for a better security. Most architecture work on the assumption that data's gradient could not leak…
Membership inference attacks (MIAs) are used to test practical privacy of machine learning models. MIAs complement formal guarantees from differential privacy (DP) under a more realistic adversary model. We analyse MIA vulnerability of…
Wearable data serves various health monitoring purposes, such as determining activity states based on user behavior and providing tailored exercise recommendations. However, the individual data perception and computational capabilities of…
Adapting Large Language Models (LLMs) to specific tasks introduces concerns about computational efficiency, prompting an exploration of efficient methods such as In-Context Learning (ICL). However, the vulnerability of ICL to privacy…
Large Language Models (LLMs) have the promise to revolutionize computing broadly, but their complexity and extensive training data also expose significant privacy vulnerabilities. One of the simplest privacy risks associated with LLMs is…
The increasing complexity of algorithms for analyzing medical data, including de-identification tasks, raises the possibility that complex algorithms are learning not just the general representation of the problem, but specifics of given…
The information leakage of a cryptographic implementation with a given degree of protection is evaluated in a typical situation when the signal-to-noise ratio is small. This is solved by expanding Kullback-Leibler divergence, entropy, and…
We introduce an analytical framework to quantify the changes in a machine learning algorithm's output distribution following the inclusion of a few data points in its training set, a notion we define as leave-one-out distinguishability…