As the deployment of pre-trained language models (PLMs) expands, pressing security
concerns have arisen regarding the potential for malicious extraction of training data, posing …

Rapid advancements in language models (LMs) have led to their adoption across many
sectors. Alongside the potential benefits, such models present a range of risks, including …

A key component of generating text from modern language models (LM) is the selection and
tuning of decoding algorithms. These algorithms determine how to generate text from the …

Large-scale natural language processing models have been developed and integrated into
numerous applications, given the advantage of their remarkable performance. Nonetheless …

Recent research findings suggest that machine learning models are highly susceptible to
backdoor poisoning attacks. Backdoor poisoning attacks can be easily executed and …

The exponential growth of digital content has generated massive textual datasets,
necessitating the use of advanced analytical approaches. Large Language Models (LLMs) …

Recently, model stealing attacks are widely studied but most of them are focused on stealing
a single non-discrete model, eg, neural networks. For ensemble models, these attacks are …

Education in cybersecurity is crucial in the current society, and it will be extended into the
artificial intelligence (AI) area, called AI security, in the near future. Although many video …

Embedding as a Service (EaaS) has become a widely adopted solution, which offers feature
extraction capabilities for addressing various downstream tasks in Natural Language …

With the growing burden of training deep learning models with huge datasets, transfer
learning has been widely adopted (eg, Transformers like BERT, GPT). Transfer learning …