The adoption of large language models (LLMs) in healthcare demands a careful analysis of
their potential to spread false medical knowledge. Because LLMs ingest massive volumes of …

Backdoor attacks are commonly executed by contaminating training data, such that a trigger
can activate predetermined harmful effects during the test phase. In this work, we present …

Backdoor Attacks have been a serious vulnerability against Large Language Models
(LLMs). However, previous methods only reveal such risk in specific models, or present …

Recent literature has shown that LLMs are vulnerable to backdoor attacks, where malicious
attackers inject a secret token sequence (ie, trigger) into training prompts and enforce their …

Pre-training has been a necessary phase for deploying pre-trained language models
(PLMs) to achieve remarkable performance in downstream tasks. However, we empirically …

Leveraging the rapid development of Large Language Models LLMs, LLM-based agents
have been developed to handle various real-world applications, including finance …

Large language models (LLMs) have raised concerns about potential security threats
despite performing significantly in Natural Language Processing (NLP). Backdoor attacks …

Deep learning neural network (DNN) models are currently experiencing significant success
in domains like image classification. In the realm of power grids, there have been numerous …

In smart grids, the robustness and reliability of the transmission system depend on the
operational integrity of the insulators. The success of deep learning has facilitated the …