Defending Against Patch-based Backdoor Attacks on Self-Supervised Learning

被引:5
作者
Tejankar, Ajinkya [1 ]
Sanjabi, Maziar [2 ]
Wang, Qifan [2 ]
Wang, Sinong [2 ]
Firooz, Hamed [2 ]
Pirsiavash, Hamed [1 ]
Tan, Liang [2 ]
机构
[1] Univ Calif Davis, Davis, CA 95616 USA
[2] Meta AI, Delaware, OH USA
来源
2023 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR) | 2023年
关键词
D O I
10.1109/CVPR52729.2023.01178
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Recently, self-supervised learning (SSL) was shown to be vulnerable to patch-based data poisoning backdoor attacks. It was shown that an adversary can poison a small part of the unlabeled data so that when a victim trains an SSL model on it, the final model will have a backdoor that the adversary can exploit. This work aims to defend self-supervised learning against such attacks. We use a three-step defense pipeline, where we first train a model on the poisoned data. In the second step, our proposed defense algorithm (PatchSearch) uses the trained model to search the training data for poisoned samples and removes them from the training set. In the third step, a final model is trained on the cleaned-up training set. Our results show that PatchSearch is an effective defense. As an example, it improves a model's accuracy on images containing the trigger from 38.2% to 63.7% which is very close to the clean model's accuracy, 64.6%. Moreover, we show that PatchSearch outperforms baselines and state-of-the-art defense approaches including those using additional clean, trusted data. Our code is available at https://github.com/UCDvision/PatchSearch
引用
收藏
页码:12239 / 12249
页数:11
相关论文
共 56 条
  • [41] Selvaraju RR, 2020, INT J COMPUT VISION, V128, P336, DOI [10.1007/s11263-019-01228-7, 10.1109/ICCV.2017.74]
  • [42] Shafahi Ali, 2018, Advances in Neural Information Processing Systems
  • [43] Srivastava B., 2018, ARXIV181103728
  • [44] Tejankar Ajinkya, 2021, P IEEE CVF INT C COM
  • [45] Tian Yonglong, 2020, ADV NEURAL INFORM PR, V33
  • [46] Tran Brandon, 2018, Advances in neural information processing systems (NeurIPS)
  • [47] Turner A., 2019, OpenReview
  • [48] High-Voltage Electrolytes for Aqueous Energy Storage Devices
    Wan, Fang
    Zhu, Jiacai
    Huang, Shuo
    Niu, Zhiqiang
    [J]. BATTERIES & SUPERCAPS, 2020, 3 (04) : 323 - 330
  • [49] Neural Cleanse: Identifying and Mitigating Backdoor Attacks in Neural Networks
    Wang, Bolun
    Yao, Yuanshun
    Shan, Shawn
    Li, Huiying
    Viswanath, Bimal
    Zheng, Haitao
    Zhao, Ben Y.
    [J]. 2019 IEEE SYMPOSIUM ON SECURITY AND PRIVACY (SP 2019), 2019, : 707 - 723
  • [50] Unsupervised Feature Learning via Non-Parametric Instance Discrimination
    Wu, Zhirong
    Xiong, Yuanjun
    Yu, Stella X.
    Lin, Dahua
    [J]. 2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2018, : 3733 - 3742