Kallima: A Clean-Label Framework for Textual Backdoor Attacks
- 25 September 2022
- book chapter
- conference paper
- Published by Springer Science and Business Media LLC
Abstract
No abstract availableKeywords
This publication has 25 references indexed in Scilit:
- A Backdoor Attack Against LSTM-Based Text Classification SystemsIEEE Access, 2019
- Auditing Data Provenance in Text-Generation ModelsPublished by Association for Computing Machinery (ACM) ,2019
- Neural Cleanse: Identifying and Mitigating Backdoor Attacks in Neural NetworksPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2019
- Sentence-BERT: Sentence Embeddings using Siamese BERT-NetworksPublished by Association for Computational Linguistics (ACL) ,2019
- Predicting the Type and Target of Offensive Posts in Social MediaPublished by Association for Computational Linguistics (ACL) ,2019
- TextBugger: Generating Adversarial Text Against Real-world ApplicationsPublished by Internet Society ,2019
- Asking for a FriendPublished by Association for Computing Machinery (ACM) ,2018
- Know What You Don’t Know: Unanswerable Questions for SQuADPublished by Association for Computational Linguistics (ACL) ,2018
- Membership Inference Attacks Against Machine Learning ModelsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2017
- Improving Neural Machine Translation Models with Monolingual DataPublished by Association for Computational Linguistics (ACL) ,2016