Federated learning has emerged as an effective paradigm to achieve privacy-preserving
collaborative learning among different parties. Compared to traditional centralized learning …

Transfer learning is a popular software reuse technique in the deep learning community that
enables developers to build custom models (students) based on sophisticated pretrained …

Measuring similarity of neural networks has become an issue of great importance and
research interest to understand and utilize differences of neural networks. While there are …

An off-the-shelf model as a commercial service could be stolen by model stealing attacks,
posing great threats to the rights of the model owner. Model fingerprinting aims to verify …

The rapid advancements in pre-trained Large Language Models (LLMs) and Large
Multimodal Models (LMMs) have ushered in a new era of intelligent applications …

Training deep neural network (DNN) models, which has become an important task in today's
software development, is often costly in terms of computational resources and time. With the …

With the widespread application in industrial manufacturing and commercial services, well-
trained deep neural networks (DNNs) are becoming increasingly valuable and crucial …

Given a well-behaved neural network is possible to identify its parent based on which it was
tuned? In this paper we introduce a novel task known as neural lineage detection aiming at …

Definitions of the distance between two machine learning models either characterize the
similarity of the models' predictions or of their weights. While similarity of weights is attractive …

Deep learning has been widely applied in solving many tasks, such as image recognition,
speech recognition, and natural language processing. It requires a high-quality dataset …