Mainstream backdoor attack methods typically demand substantial tuning data for
poisoning, limiting their practicality and potentially degrading the overall performance when …

Although recent personalization methods have democratized high-resolution image
synthesis by enabling swift concept acquisition with minimal examples and lightweight …

While deep learning models have shown significant performance across various domains,
their deployment needs extensive resources and advanced computing infrastructure. As a …

Backdoor attacks pose a serious threat to federated systems, where malicious clients
optimize on the triggered distribution to mislead the global model towards a predefined …

With the rising popularity of Large Language Models (LLMs), assessing their trustworthiness
through security tasks has gained critical importance. Regarding the new task of universal …

Due to the advantages of privacy-preserving, Federated Learning (FL) is widely used in
distributed machine learning systems. However, existing FL methods suffer from low …

The advancement of Machine Learning has enabled the widespread deployment of
Machine Learning as a Service (MLaaS) applications. However, the untrustworthy nature of …