[Paper Summary] "BadPre: Task-agnostic Backdoor Attacks to Pre-trained NLP Foundation Models"
Original Paper Link: https://arxiv.org/pdf/2110.02467.pdf Abstract The paper introduces a new backdoor attack method on pre-trained NLP...
I'm a final year undergraduate student in computer engineering at Hong Kong University of Science and Technology (HKUST) in the School of Engineering. My research interests rely on Trustworthy AI and robustness of deep neural networks. Especially, I am fascinated by both adversarial attack as well as adversarial training to overcome the vulnerability of various machine learning models in wide range of domains. I am also interested in exploring other fields of study such as the relationship between adversarial attack and federated learning, backdoor attacks/defense, fairness, and natural language processing.