 Attention-Enhancing Backdoor Attacks Against BERT-based ModelsConference on Empirical Methods in Natural Language Processing (EMNLP), 2023 |
 A Study of the Attention Abnormality in Trojaned BERTsNorth American Chapter of the Association for Computational Linguistics (NAACL), 2022 |
 Security for Machine Learning-based Software Systems: a survey of
threats, practices and challengesACM Computing Surveys (ACM CSUR), 2022 |
 Deep Learning BackdoorsSecurity and Artificial Intelligence (SAI), 2020 |
