1. Concealed Data Poisoning Attacks on NLP Models
2. Be Careful about Poisoned Word Embeddings: Exploring the Vulnerability of the Embedding Layers in NLP Models
3. Subpopulation data poisoning attacks;jagielski;arXiv preprint arXiv 2006 14080,2020
4. Witches’ brew: Industrial scale data poisoning via gradient matching;geiping;arXiv preprint arXiv 2009 02026,2020
5. Can you really backdoor federated learning?;sun;arXiv preprint arXiv 1911 11698,2019