Related papers: Exploring Connections Between Active Learning and …
Machine unlearning has become a promising solution for fulfilling the "right to be forgotten", under which individuals can request the deletion of their data from machine learning models. However, existing studies of machine unlearning…
Graph-structured data, which captures non-Euclidean relationships and interactions between entities, is growing in scale and complexity. As a result, training state-of-the-art graph machine learning (GML) models have become increasingly…
Model extraction is a growing concern for the security of AI systems. For deep neural network models, the architecture is the most important information an adversary aims to recover. Being a sequence of repeated computation blocks, neural…
Deep learning driven by large neural network models is overtaking traditional machine learning methods for understanding unstructured and perceptual data domains such as speech, text, and vision. At the same time, the "as-a-Service"-based…
Large Language Models (LLMs) are prone to memorizing training data, which poses serious privacy risks. Two of the most prominent concerns are training data extraction and Membership Inference Attacks (MIAs). Prior research has shown that…
Many of today's machine learning (ML) systems are built by reusing an array of, often pre-trained, primitive models, each fulfilling distinct functionality (e.g., feature extraction). The increasing use of primitive models significantly…
Machine learning as a service (MLaaS), and algorithm marketplaces are on a rise. Data holders can easily train complex models on their data using third party provided learning codes. Training accurate ML models requires massive labeled data…
Model stealing attack is increasingly threatening the confidentiality of machine learning models deployed in the cloud. Recent studies reveal that adversaries can exploit data synthesis techniques to steal machine learning models even in…
The collection and availability of big data, combined with advances in pre-trained models (e.g., BERT, XLNET, etc), have revolutionized the predictive performance of modern natural language processing tasks, ranging from text classification…
Today, machine learning is widely applied in sensitive, security-related, and financially lucrative applications. Model extraction attacks undermine current business models where a model owner sells model access, e.g., via MLaaS APIs.…
Building advanced machine learning (ML) models requires expert knowledge and many trials to discover the best architecture and hyperparameter settings. Previous work demonstrates that model information can be leveraged to assist other…
A learned database system uses machine learning (ML) internally to improve performance. We can expect such systems to be vulnerable to some adversarial-ML attacks. Often, the learned component is shared between mutually-distrusting users or…
Machine Unlearning (MU) has recently gained considerable attention due to its potential to achieve Safe AI by removing the influence of specific data from trained Machine Learning (ML) models. This process, known as knowledge removal,…
Deep learning has emerged as a strong and efficient framework that can be applied to a broad spectrum of complex learning problems which were difficult to solve using the traditional machine learning techniques in the past. In the last few…
Powered by machine learning services in the cloud, numerous learning-driven mobile applications are gaining popularity in the market. As deep learning tasks are mostly computation-intensive, it has become a trend to process raw data on…
Modern machine learning (ML) ecosystems offer a surging number of ML frameworks and code repositories that can greatly facilitate the development of ML models. Today, even ordinary data holders who are not ML experts can apply off-the-shelf…
In privacy-preserving machine learning, it is common that the owner of the learned model does not have any physical access to the data. Instead, only a secured remote access to a data lake is granted to the model owner without any ability…
Self-supervised models are increasingly prevalent in machine learning (ML) since they reduce the need for expensively labeled data. Because of their versatility in downstream applications, they are increasingly used as a service exposed via…
Collaborative machine learning and related techniques such as federated learning allow multiple participants, each with his own training dataset, to build a joint model by training locally and periodically exchanging model updates. We…
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…