Recent studies revealed that deep learning is susceptible to backdoor poisoning attacks. An
adversary can embed a hidden backdoor into a model to manipulate its predictions by only …

Self-supervised learning in computer vision trains on unlabeled data, such as images or
(image, text) pairs, to obtain an image encoder that learns high-quality embeddings for input …

Prompt-based learning is vulnerable to backdoor attacks. Existing backdoor attacks against
prompt-based models consider injecting backdoors into the entire embedding layers or word …

The huge training overhead, considerable commercial value, and various potential security
risks make it urgent to protect the intellectual property (IP) of Deep Neural Networks (DNNs) …

Large Language Models (LLMs) are increasingly deployed as the backend for a variety of
real-world applications called LLM-Integrated Applications. Multiple recent works showed …

Recent studies have revealed that\textit {Backdoor Attacks} can threaten the safety of natural
language processing (NLP) models. Investigating the strategies of backdoor attacks will help …

The pre-training-then-fine-tuning paradigm has been widely used in deep learning. Due to
the huge computation cost for pre-training, practitioners usually download pre-trained …

The advancement of large language models (LLMs) has significantly enhanced the ability to
effectively tackle various downstream NLP tasks and unify these tasks into generative …

Backdoor attacks for neural code models have gained considerable attention due to the
advancement of code intelligence. However, most existing works insert triggers into task …

Reproducibility is crucial to the advancement of science; it strengthens confidence in
seemingly contradictory results and expands the boundaries of known discoveries …