Distilling Robust and Non-Robust Features in Adversarial Examples by Information Bottleneck

Authors: Junho Kim, Byung-Kwan Lee, Yong Man Ro

NeurIPS 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Through comprehensive experiments, we demonstrate that the distilled features are highly correlated with adversarial prediction, and they have human-perceptible semantic information by themselves.
Researcher Affiliation Academia School of Electrical Engineering Korea Advanced Institute of Science and Technology (KAIST) {arkimjh, leebk, ymro}@kaist.ac.kr
Pseudocode No No structured pseudocode or algorithm blocks were found in the paper. Figure 1 presents a diagram of the bottleneck concept, but it is not pseudocode.
Open Source Code No The paper does not provide any explicit statements about releasing source code or links to a code repository for the described methodology.
Open Datasets Yes Table 1: Classification accuracy of model performance attacked by FGSM [2], PGD [7], and CW [4] on VGG-16 [29] and WRN-28-10 [30], adversarially trained with γ = 0.03 for CIFAR-10, SVHN, and Tiny-Image Net. and publicly available datasets [32, 33, 34].
Dataset Splits No The paper uses standard datasets like CIFAR-10, SVHN, and Tiny-Image Net, but does not explicitly state the specific training, validation, and test dataset splits (e.g., percentages or sample counts) used for reproducibility.
Hardware Specification No The paper does not provide specific hardware details such as GPU or CPU models, memory, or specific computing environments used for running the experiments.
Software Dependencies No The paper does not provide specific software dependencies or version numbers (e.g., programming language versions, library versions) required to replicate the experiments.
Experiment Setup Yes In this paper, we adversarially train the model f on γ = 0.03 for the standard adversarial attack.