关注
Zongru Wu
Zongru Wu
Shanghai Jiao Tong University
在 sjtu.edu.cn 的电子邮件经过验证
标题
引用次数
引用次数
年份
Backdoor attacks and countermeasures in natural language processing models: A comprehensive security review
P Cheng, Z Wu, W Du, G Liu
arXiv preprint arXiv:2309.06055, 2023
92023
TrojanRAG: Retrieval-Augmented Generation Can Be Backdoor Driver in Large Language Models
P Cheng, Y Ding, T Ju, Z Wu, W Du, P Yi, Z Zhang, G Liu
arXiv preprint arXiv:2405.13401, 2024
12024
Syntactic Ghost: An Imperceptible General-purpose Backdoor Attacks on Pre-trained Language Models
P Cheng, W Du, Z Wu, F Zhang, L Chen, G Liu
arXiv preprint arXiv:2402.18945, 2024
2024
Acquiring Clean Language Models from Backdoor Poisoned Datasets by Downscaling Frequency Space
Z Wu, Z Zhang, P Cheng, G Liu
arXiv preprint arXiv:2402.12026, 2024
2024
系统目前无法执行此操作，请稍后再试。
文章 1–4
共建清朗的网络空间,如遇有害信息,请举报。
本站数据皆整合自互联网公开资源索引,方便科研学术方面查询,并不存储相关数据资源;如对此有异议,请联系我们解决.
© 2023 学术资源搜索   @联系我们 | 申请短期会员 | 数据源提交