Mixup Inference: Better Exploiting Mixup to Defend Adversarial Attacks

Authors: Tianyu Pang*, Kun Xu*, Jun Zhu

ICLR 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Our experiments on CIFAR-10 and CIFAR-100 demonstrate that MI can further improve the adversarial robustness for the models trained by mixup and its variants. In this section, we provide the experimental results on CIFAR-10 and CIFAR-100 (Krizhevsky & Hinton, 2009) to demonstrate the effectiveness of our MI methods on defending adversarial attacks.
Researcher Affiliation Collaboration Tianyu Pang , Kun Xu , Jun Zhu Dept. of Comp. Sci. & Tech., BNRist Center, Institute for AI, Tsinghua University; Real AI {pty17,xu-k16}@mails.tsinghua.edu.cn, dcszj@tsinghua.edu.cn
Pseudocode Yes Algorithm 1 Mixup Inference (MI)
Open Source Code Yes Our codes are available at https://github.com/P2333/Mixup-Inference.
Open Datasets Yes In experiments, we evaluate MI on CIFAR-10 and CIFAR-100 (Krizhevsky & Hinton, 2009)
Dataset Splits No The paper mentions using CIFAR-10 and CIFAR-100 for training and testing, but it does not explicitly specify a validation dataset split or its size.
Hardware Specification Yes Most of our experiments are conducted on the NVIDIA DGX-1 server with eight Tesla P100 GPUs.
Software Dependencies No The paper does not specify software dependencies with version numbers (e.g., Python, PyTorch, TensorFlow versions).
Experiment Setup Yes In training, we use Res Net-50 (He et al., 2016) and apply the momentum SGD optimizer (Qian, 1999) on both CIFAR-10 and CIFAR-100. We run the training for 200 epochs with the batch size of 64. The initial learning rate is 0.01 for ERM, mixup and AT; 0.1 for interpolated AT (Lamb et al., 2019). The learning rate decays with a factor of 0.1 at 100 and 150 epochs.