Fetching the paper…
Reading the bibliography…
Backdoor attack intends to embed hidden backdoor into deep neural networks (DNNs), such that the attacked model performs well on benign samples, whereas its prediction will be maliciously changed if the hidden backdoor is activated by the attacker defined trigger.
Design and evaluation of a multi-domain trojan detection method on deep neural networks, 2019
Yansong Gao, Yeonjae Kim, Bao Gia Doan, Zhi Zhang, Gongxuan Zhang, Surya Nepal, Damith C. Ranasinghe, and Hyoungshick Kim · 2019
Earlier work this paper cites.
Badnets: Identifying vulnerabilities in the machine learning model supply chain, 2019
Tianyu Gu, Brendan Dolan-Gavitt, and Siddharth Garg · 2019
Earlier work this paper cites.
Onion: A simple and effective defense against textual backdoor attacks, 2021
Fanchao Qi, Yangyi Chen, Mukai Li, Yuan Yao, Zhiyuan Liu, and Maosong Sun · 2021
Cited alongside, same era.
Rap: Robustness-aware perturbations for defending against backdoor attacks on nlp models, 2021
Wenkai Yang, Yankai Lin, Peng Li, Jie Zhou, and Xu Sun · 2021
Cited alongside, same era.
Bert-base-uncased, https://huggingface.co/models
Cited in the paper.
Rap: Robustness-aware perturbations for defending against backdoor attacks on nlp models, https://github.com/lancopku/rap
Cited in the paper.
Rethinking stealthiness of backdoor attack against nlp models, https://github.com/lancopku/sos
Cited in the paper.
Ripple: Restricted inner product poison learning, https://github.com/neulab/ripple
Cited in the paper.
Rethinking stealthiness of backdoor attack against NLP models
Wenkai Yang, Yankai Lin, Peng Li, Jie Zhou, and Xu Sun · 2021
Later among the works it cites.
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…