Feature Prioritization and Regularization Improve Standard Accuracy and Adversarial Robustness

Authors: Chihuang Liu, Joseph JaJa

IJCAI 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental In this section, we evaluate our model on the MNIST, CIFAR10 and CIFAR-100 datasets, and present empirical justification to attention module and some quantitative and qualitative results.
Researcher Affiliation Academia Chihuang Liu and Joseph Ja Ja Institute for Advanced Computer Studies and Department of Electrical and Computer Engineering University of Maryland, College Park, MD 20742, USA {chliu, josephj}@umd.edu
Pseudocode No The paper provides mathematical formulations and descriptions of its model, but no explicit pseudocode or algorithm blocks.
Open Source Code No The paper does not provide any explicit statement or link indicating that its source code is open-sourced or publicly available.
Open Datasets Yes Our model is evaluated on the MNIST, CIFAR-10, and CIFAR-100 datasets
Dataset Splits No The paper mentions training and testing phases and refers to the 'test set' but does not specify detailed train/validation/test splits (e.g., percentages or sample counts).
Hardware Specification No The paper does not provide specific hardware details (e.g., CPU or GPU models) used for running the experiments.
Software Dependencies No The paper does not specify any software dependencies with version numbers (e.g., Python, PyTorch, TensorFlow versions).
Experiment Setup Yes We use a CNN with two convolutional layers with 32 and 64 filters respectively, followed by two fully connected layers of size 1024 and 10. The network is trained with 40-step PGD adversary with a step size of 0.01 and l bound of = 0.3. The settings are the same as in Madry et al. [2017].