1 code implementation • 19 Feb 2024 • Zihao Luo, Xilie Xu, Feng Liu, Yun Sing Koh, Di Wang, Jingfeng Zhang
To mitigate this issue, we propose Stable PrivateLoRA that adapts the LDM by minimizing the ratio of the adaptation loss to the MI gain, which implicitly rescales the gradient and thus stabilizes the optimization.
no code implementations • 3 Oct 2023 • Xilie Xu, Jingfeng Zhang, Mohan Kankanhalli
To mitigate this issue, we propose a low-rank (LoRa) branch that disentangles RFT into two distinct components: optimizing natural objectives via the LoRa branch and adversarial objectives via the FE.
1 code implementation • NeurIPS 2023 • Xilie Xu, Jingfeng Zhang, Feng Liu, Masashi Sugiyama, Mohan Kankanhalli
To improve transferability, the existing work introduced the standard invariant regularization (SIR) to impose style-independence property to SCL, which can exempt the impact of nuisance style factors in the standard representation.
1 code implementation • NeurIPS 2023 • Xilie Xu, Jingfeng Zhang, Feng Liu, Masashi Sugiyama, Mohan Kankanhalli
Adversarial contrastive learning (ACL) does not require expensive data annotations but outputs a robust representation that withstands adversarial attacks and also generalizes to a wide range of downstream tasks.
1 code implementation • 7 Feb 2022 • Xilie Xu, Jingfeng Zhang, Feng Liu, Masashi Sugiyama, Mohan Kankanhalli
Furthermore, we theoretically find that the adversary can also degrade the lower bound of a TST's test power, which enables us to iteratively minimize the test criterion in order to search for adversarial pairs.
1 code implementation • 31 May 2021 • Jingfeng Zhang, Xilie Xu, Bo Han, Tongliang Liu, Gang Niu, Lizhen Cui, Masashi Sugiyama
First, we thoroughly investigate noisy labels (NLs) injection into AT's inner maximization and outer minimization, respectively and obtain the observations on when NL injection benefits AT.
no code implementations • 15 Feb 2021 • Chen Chen, Jingfeng Zhang, Xilie Xu, Tianlei Hu, Gang Niu, Gang Chen, Masashi Sugiyama
To enhance adversarial robustness, adversarial training learns deep neural networks on the adversarial variants generated by their natural data.
1 code implementation • ICML 2020 • Jingfeng Zhang, Xilie Xu, Bo Han, Gang Niu, Lizhen Cui, Masashi Sugiyama, Mohan Kankanhalli
Adversarial training based on the minimax formulation is necessary for obtaining adversarial robustness of trained models.