Fetching the paper…
Reading the bibliography…
Multimodal contrastive pretraining, exemplified by models like CLIP, has been found to be vulnerable to backdoor attacks.
J. Deng, W. Dong, R. Socher, L.-J. Li, K. Li, and L. Fei-Fei, “Imagenet: A large-scale hierarchical image database,” in 2009 IEEE Conference on Computer Vision and Pattern Recognition , pp. 248–255, 2009
2009
Earlier work this paper cites.
Y. Bengio, A. Courville, and P. Vincent, “Representation learning: A review and new perspectives,” IEEE Transactions on Pattern Analysis and Machine Intelligence , pp. 1798–1828, 2013
2013
Earlier work this paper cites.
2017
Earlier work this paper cites.
2017
Earlier work this paper cites.
2017
Earlier work this paper cites.
I. Loshchilov, “Decoupled weight decay regularization,” arXiv preprint arXiv:1711.05101 , 2017
2017
Earlier work this paper cites.
2018
Earlier work this paper cites.
P. Sharma, N. Ding, S. Goodman, and R. Soricut, “Conceptual captions: A cleaned, hypernymed, image alt-text dataset for automatic image captioning,” in Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics , pp. 2556–2565, 2018
2018
Earlier work this paper cites.
J. Wei and K. Zou, “EDA: Easy Data Augmentation Techniques for Boosting Performance on Text Classification Tasks,” in Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing , pp. 6382–6388, 2019
2019
Earlier work this paper cites.
Weng, C., Lee, Y. & Wu, S. On the Trade-off between Adversarial and Backdoor Robustness.. Conference On Neural Information Processing Systems
2020
Earlier work this paper cites.
Gan, Z., Chen, Y., Li, L., Zhu, C., Cheng, Y. & Liu, J. Large-Scale Adversarial Training for Vision-and-Language Representation Learning.. Conference On Neural Information Processing Systems
2020
Earlier work this paper cites.
I. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, A. Courville, and Y. Bengio, “Generative adversarial networks,” Communications of the ACM , pp. 139–144, 2020
2020
Earlier work this paper cites.
A. Radford, J. W. Kim, C. Hallacy, A. Ramesh, G. Goh, S. Agarwal, G. Sastry, A. Askell, P. Mishkin, J. Clark, et al. , “Learning transferable visual models from natural language supervision,” in International Conference on Machine Learning , PMLR, pp. 8748–8763, 2021
2021
Earlier work this paper cites.
C. Jia, Y. Yang, Y. Xia, Y.-T. Chen, Z. Parekh, H. Pham, Q. Le, Y.-H. Sung, Z. Li, and T. Duerig, ”Scaling up visual and vision-language representation learning with noisy text supervision,” in Proc. Int. Conf. Machine Learning
2021
Earlier work this paper cites.
2021
Cited alongside, same era.
Y. Li, X. Lyu, N. Koren, L. Lyu, B. Li, and X. Ma, “Neural Attention Distillation: Erasing Backdoor Triggers from Deep Neural Networks,” International Conference on Learning Representations , 2021
2021
Cited alongside, same era.
Y. Li, X. Lyu, N. Koren, L. Lyu, B. Li, and X. Ma, “Anti-Backdoor Learning: Training Clean Models on Poisoned Data,” Conference on Neural Information Processing Systems , pp. 14900-14912, 2021
2021
Cited alongside, same era.
D. Wu and Y. Wang, “Adversarial neuron pruning purifies backdoored deep models,” Conference on Neural Information Processing Systems , pp. 16913–16925, 2021
2021
Cited alongside, same era.
S. Feng, G. Tao, S. Cheng, G. Shen, X. Xu, Y. Liu, K. Zhang, S. Ma, and X. Zhang, “Detecting Backdoors in Pre-trained Encoders,” Computer Vision and Pattern Recognition , pp. 16352-16362, 2023
2023
Later among the works it cites.
H. Bansal, N. Singhi, Y. Yang, F. Yin, A. Grover, and K.-W. Chang, “Cleanclip: Mitigating data poisoning attacks in multimodal contrastive learning,” in Proceedings of the IEEE/CVF International Conference on Computer Vision , 2023, pp. 112–123
2023
Later among the works it cites.
M. Xue, Y. Wu, Z. Wu, Y. Zhang, J. Wang, and W. Liu, “Detecting backdoor in deep neural networks via intentional adversarial perturbations,” Information Sciences , vol. 634, pp. 564–577, 2023
2023
Later among the works it cites.
S. Wei, M. Zhang, H. Zha, and B. Wu, “Shared adversarial unlearning: Backdoor mitigation by unlearning shared adversarial examples,” Conference on Neural Information Processing Systems , 2023
2023
Later among the works it cites.
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…
2021
Cited alongside, same era.
B. Koonce, “ResNet 50,” Convolutional Neural Networks with Swift for TensorFlow: Image Recognition and Dataset Categorization , pp. 63–72, 2021
2021
Cited alongside, same era.
K. Han, A. Xiao, E. Wu, J. Guo, C. Xu, and Y. Wang, “Transformer in transformer,” Advances in Neural Information Processing Systems , pp. 15908–15919, 2021
2021
Cited alongside, same era.
N. Carlini and A. Terzis, “Poisoning and Backdooring Contrastive Learning,” in International Conference on Learning Representations , 2022
2022
Cited alongside, same era.
J. Jia, Y. Liu, and N. Gong, “BadEncoder: Backdoor Attacks to Pre-trained Encoders in Self-Supervised Learning,” IEEE Symposium on Security and Privacy , pp. 2043-2059, 2022
2022
Cited alongside, same era.
Y. Zeng, S. Chen, W. Park, Z. Mao, M. Jin, and R. Jia, “Adversarial unlearning of backdoors via implicit hypergradient,” International Conference on Learning Representations , 2022
2022
Cited alongside, same era.
N. Mu, A. Kirillov, D. Wagner, and S. Xie, “SLIP: Self-Supervision Meets Language-Image Pre-Training,” in Proceedings of the European Conference on Computer Vision , pp. 529–544, 2022
2022
Cited alongside, same era.
S. Goel, H. Bansal, S. Bhatia, R. Rossi, V. Vinay, and A. Grover, “CyCLIP: Cyclic Contrastive Language-Image Pretraining,” Advances in Neural Information Processing Systems , pp. 6704–6719, 2022
2022
Cited alongside, same era.
B. Mu, Z. Niu, L. Wang, X. Wang, Q. Miao, R. Jin, and G. Hua, “Progressive backdoor erasing via connecting backdoor and adversarial attacks,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pp. 20495–20503, 2023
2023
Later among the works it cites.
Z. Zhou, S. Hu, M. Li, H. Zhang, Y. Zhang, and H. Jin, “Advclip: Downstream-agnostic adversarial examples in multimodal contrastive learning,” in Proceedings of the 31st ACM International Conference on Multimedia , pp. 6311–6320, 2023
2023
Later among the works it cites.
N. Carlini, M. Jagielski, C. A. Choquette-Choo, D. Paleka, W. Pearce, H. Anderson, A. Terzis, K. Thomas, and F. Tramèr, “Poisoning Web-Scale Training Datasets is Practical,” in 2024 IEEE Symposium on Security and Privacy , IEEE Computer Society, pp. 176–176, 2024
2024
Closest in time.
J. Bai, K. Gao, S. Min, S. Xia, Z. Li, and W. Liu, “BadCLIP: Trigger-Aware Prompt Learning for Backdoor Attacks on CLIP,” IEEE/CVF Conference on Computer Vision and Pattern Recognition , 2024
2024
Closest in time.
W. Yang, J. Gao, and B. Mirzasoleiman, “Robust contrastive language-image pretraining against data poisoning and backdoor attacks,” Advances in Neural Information Processing Systems , 2024
2024
Closest in time.
Gao, Y., Wu, D., Zhang, J., Gan, G., Xia, S., Niu, G. & Sugiyama, M. On the Effectiveness of Adversarial Training Against Backdoor Attacks. IEEE Transactions On Neural Networks And Learning Systems
2024
Closest in time.
P.-F. Zhang, Z. Huang, and G. Bai, “Universal adversarial perturbations for vision-language pre-trained models,” Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval , pp. 862–871, 2024
2024
Closest in time.
Z. Niu, Y. Sun, Q. Miao, R. Jin, and G. Hua, “Towards unified robustness against both backdoor and adversarial attacks,” IEEE Transactions on Pattern Analysis and Machine Intelligence , pp. 1–16, 2024
2024
Closest in time.
Y. Li, F. Liang, L. Zhao, Y. Cui, W. Ouyang, J. Shao, F. Yu, and J. Yan, “Supervision Exists Everywhere: A Data Efficient Contrastive Language-Image Pre-training Paradigm,” in Proceedings of the International Conference on Learning Representations , 2024
2024
Closest in time.
S. Liang, M. Zhu, A. Liu, B. Wu, X. Cao, and E.-C. Chang, “Badclip: Dual-embedding guided backdoor attack on multimodal contrastive learning,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pp. 24645–24654, 2024
2024
Closest in time.