To solve complex tasks, large language models (LLMs) often require multi...
Vision-language models (VLMs) have recently demonstrated strong efficacy...
Pre-trained language models (PLMs) serve as backbones for various real-w...
This paper reexamines the research on out-of-distribution (OOD) robustne...
Textual adversarial attacks can discover models' weaknesses by adding
se...
Pre-trained language models (PLMs) achieve remarkable performance on man...
Textual adversarial samples play important roles in multiple subfields o...
Textual backdoor attacks are a kind of practical threat to NLP systems. ...
Prompt-based learning paradigm bridges the gap between pre-training and
...
Despite great success on many machine learning tasks, deep neural networ...
Backdoor attacks are a kind of emergent security threat in deep learning...
Adversarial attacks and backdoor attacks are two common security threats...
Recently, the textual adversarial attack models become increasingly popu...
A sememe is defined as the minimum semantic unit in linguistics. Sememe
...
Backdoor attacks are a kind of insidious security threat against machine...
Backdoor attacks, which are a kind of emergent training-time threat to d...