Abstract Large Language Models (LLMs), such as ChatGPT and Bard, have revolutionized
natural language understanding and generation. They possess deep language …

Machine-Learning-as-a-Service (MLaaS) has become a widespread paradigm, making
even the most complex Machine Learning models available for clients via, eg, a pay-per …

Current model extraction attacks assume that the adversary has access to a surrogate
dataset with characteristics similar to the proprietary data used to train the victim model. This …

Abstract Machine learning models deployed as a service (MLaaS) are susceptible to model
stealing attacks, where an adversary attempts to steal the model within a restricted access …

The practice of transferring knowledge from a sophisticated, proprietary large language
model (LLM) to a compact, open-source LLM has garnered considerable attention. Previous …

We investigate whether model extraction can be used to 'steal'the weights of sequential
recommender systems, and the potential threats posed to victims of such attacks. This type …

Deep Neural Network (DNN) models become one of the most valuable enterprise assets
due to their critical roles in all aspects of applications. With the trend of privatization …

Abstract Data-Free Model Extraction (DFME) aims to clone a black-box model without
knowing its original training data distribution, making it much easier for attackers to steal …

In the last decade, many deep learning models have been well trained and made a great
success in various fields of machine intelligence, especially for computer vision and natural …

Pre-trained encoders are general-purpose feature extractors that can be used for many
downstream tasks. Recent progress in self-supervised learning can pre-train highly effective …