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 …

Deepfakes refer to content synthesized using deep generators, which, when misused, have
the potential to erode trust in digital media. Synthesizing high-quality deepfakes requires …

Model extraction attack typically refers to extracting non-public information from a black-box
machine learning model. Its unauthorized nature poses significant threat to intellectual …

Deep neural network (DNN) models are valuable intellectual property of model owners,
constituting a competitive advantage. Therefore, it is crucial to develop techniques to protect …

Graph neural networks (GNNs) have emerged as a state-of-the-art approach to model and
draw inferences from large scale graph-structured data in various application settings such …

Model extraction attacks (MEAs) enable an attacker to replicate the functionality of a victim
deep neural network (DNN) model by only querying its API service remotely, posing a …

Due to their capacity for image generation, GAN models may be considered as a solution for
the use of private data, which enhances their commercial value. However, unlike …

Deep neural network model extraction attack is the process of retraining a surrogate model
based on the outputs of a target model with a given set of inputs. Such attacks are hard to …

Model extraction attacks are a kind of attacks where an adversary obtains a machine
learning model whose performance is comparable with one of the victim model through …

Vision-language models have flourished these years and are regarded as promising
solutions to vision-language tasks. However, training vision-language models always …