Detecting Backdoors in Pre-trained Encoders

被引：0
|
作者：
Feng, Shiwei [1 ]
Tao, Guanhong [1 ]
Cheng, Siyuan [1 ]
Shen, Guangyu [1 ]
Xu, Xiangzhe [1 ]
Liu, Yingqi [1 ]
Zhang, Kaiyuan [1 ]
Ma, Shiqing [2 ]
Zhang, Xiangyu [1 ]
机构：
[1] Purdue University, United States
[2] Rutgers University, United States
来源：
arXiv | 2023年
关键词：
D O I：
暂无
中图分类号：
学科分类号：
摘要：
Supervised learning
引用
收藏
相关论文
共 50 条
  • [1] Detecting Backdoors in Pre-trained Encoders
    Feng, Shiwei
    Tao, Guanhong
    Cheng, Siyuan
    Shen, Guangyu
    Xu, Xiangzhe
    Liu, Yingqi
    Zhang, Kaiyuan
    Ma, Shiqing
    Zhang, Xiangyu
    2023 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2023, : 16352 - 16362
  • [2] Removing Backdoors in Pre-trained Models by Regularized Continual Pre-training
    Zhu, Biru
    Cui, Ganqu
    Chen, Yangyi
    Qin, Yujia
    Yuan, Lifan
    Fu, Chong
    Deng, Yangdong
    Liu, Zhiyuan
    Sun, Maosong
    Gu, Ming
    TRANSACTIONS OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, 2023, 11 : 1608 - 1623
  • [3] AWEncoder: Adversarial Watermarking Pre-Trained Encoders in Contrastive Learning
    Zhang, Tianxing
    Wu, Hanzhou
    Lu, Xiaofeng
    Han, Gengle
    Sun, Guangling
    APPLIED SCIENCES-BASEL, 2023, 13 (06):
  • [4] Fast transformation of discriminators into encoders using pre-trained GANs
    Yu, Cheng
    Wang, Wenmin
    PATTERN RECOGNITION LETTERS, 2022, 153 : 92 - 99
  • [5] Mutual Information Guided Backdoor Mitigation for Pre-Trained Encoders
    Han, Tingxu
    Sun, Weisong
    Ding, Ziqi
    Fang, Chunrong
    Qian, Hanwei
    Li, Jiaxun
    Chen, Zhenyu
    Zhang, Xiangyu
    IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY, 2025, 20 : 3414 - 3428
  • [6] Personalized Adaptation with Pre-trained Speech Encoders for Continuous Emotion Recognition
    Minh Tran
    Yin, Yufeng
    Soleymani, Mohammad
    INTERSPEECH 2023, 2023, : 636 - 640
  • [7] Investigating Pre-trained Audio Encoders in the Low-Resource Condition
    Yang, Hao
    Zhao, Jinming
    Haffari, Gholamreza
    Shareghi, Ehsan
    INTERSPEECH 2023, 2023, : 1498 - 1502
  • [8] Multimodal Topic Segmentation of Podcast Shows with Pre-trained Neural Encoders
    Ghinassi, Iacopo
    Wang, Lin
    Newell, Chris
    Purver, Matthew
    PROCEEDINGS OF THE 2023 ACM INTERNATIONAL CONFERENCE ON MULTIMEDIA RETRIEVAL, ICMR 2023, 2023, : 602 - 606
  • [9] EncoderMI: Membership Inference against Pre-trained Encoders in Contrastive Learning
    Liu, Hongbin
    Jia, Jinyuan
    Qu, Wenjie
    Gong, Neil Zhenqiang
    CCS '21: PROCEEDINGS OF THE 2021 ACM SIGSAC CONFERENCE ON COMPUTER AND COMMUNICATIONS SECURITY, 2021, : 2081 - 2095
  • [10] Detecting Syntactic Change with Pre-trained Transformer Models
    Hou, Liwen
    Smith, David A.
    FINDINGS OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS - EMNLP 2023, 2023, : 3564 - 3574
12345