Towards Robust Detection of Adversarial Examples

Authors: Tianyu Pang, Chao Du, Yinpeng Dong, Jun Zhu

NeurIPS 2018 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We apply our method to defend various attacking methods on the widely used MNIST and CIFAR-10 datasets, and achieve significant improvements on robust predictions under all the threat models in the adversarial setting.
Researcher Affiliation Academia Tianyu Pang, Chao Du, Yinpeng Dong, Jun Zhu Dept. of Comp. Sci. & Tech., State Key Lab for Intell. Tech. & Systems BNRist Center, THBI Lab, Tsinghua University, Beijing, China {pty17, du-c14, dyp17}@mails.tsinghua.edu.cn, dcszj@mail.tsinghua.edu.cn
Pseudocode No The paper describes methods in text and uses mathematical formulas, but does not include any structured pseudocode or algorithm blocks.
Open Source Code No The paper does not provide a concrete link to source code or explicitly state that source code is available for the methodology described.
Open Datasets Yes We use the two widely studied datasets MNIST [20] and CIFAR-10 [17]. MNIST is a collection of handwritten digits with a training set of 60,000 images and a test set of 10,000 images. CIFAR-10 consists of 60,000 color images in 10 classes with 6,000 images per class. There are 50,000 training images and 10,000 test images.
Dataset Splits No The paper specifies training and test set sizes for MNIST and CIFAR-10, but it does not explicitly mention a separate validation set split or how data was partitioned for validation.
Hardware Specification No The paper mentions funding from "NVIDIA NVAIL Program, and the projects from Siemens and Intel" in the acknowledgements, but it does not specify the exact hardware (e.g., specific GPU/CPU models, memory details) used for running the experiments.
Software Dependencies No The paper does not provide specific software dependencies with version numbers (e.g., library names like PyTorch or TensorFlow with their respective versions) needed to replicate the experiments.
Experiment Setup Yes For each network, we use both the CE and RCE as the training objectives, trained by the same settings as He et al. [16]. The number of training steps for both objectives is set to be 20,000 on MNIST and 90,000 on CIFAR-10. The pixel values of images in both datasets are scaled to be in the interval [ 0.5, 0.5].