Publications

Si Chen, Yi Zeng, Jiachen T.Wang, Won Park, Xun Chen, Lingjuan Lyu, Zhuoqing Mao, Ruoxi Jia (2023). Turning a Curse Into a Blessing: Enabling Clean-Data-Free Defenses by Model Inversion. arXiv preprint arXiv:2206.07018.

PDF Cite

Mostafa Kahla, Si Chen, Hoang Anh Just, Ruoxi Jia (2022). Label-only model inversion attacks via boundary repulsion. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition 2022.

PDF Cite Code

Weiyan Shi, Si Chen, Chiyuan Zhang, Ruoxi Jia, Zhou Yu (2022). Just fine-tune twice: Selective differential privacy for large language models. The 2022 Conference on Empirical Methods in Natural Language Processing.

PDF Cite Code

Si Chen, Tianhao Wang, Ruoxi Jia (2021). Zero-Round Active Learning. arXiv preprint arXiv:2107.06703.

PDF Cite

Tianhao Wang, Si Chen, Ruoxi Jia (2021). One-round active learning. arXiv preprint arXiv:2104.11843.

PDF Cite

Yingyan Zeng, Tianhao Wang, Si Chen, Hoang Anh Just, Ran Jin, Ruoxi Jia (2021). Learning to Refit for Convex Learning Problems. 1st IEEE Conference on Secure and Trustworthy Machine Learning.

PDF Cite

Si Chen, Mostafa Kahla, Ruoxi Jia, Guo-Jun Qi (2021). Knowledge-enriched distributional model inversion attacks. Proceedings of the IEEE/CVF international conference on computer vision 2021.

PDF Cite Code

Yi Zeng, Si Chen, Won Park, Z Morley Mao, Ming Jin, Ruoxi Jia (2021). Adversarial unlearning of backdoors via implicit hypergradient. The International Conference on Learning Representations 2022.

PDF Cite Code