Functional Adversarial Attacks

Authors: Cassidy Laidlaw, Soheil Feizi

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

Reproducibility Variable Result LLM Response
Research Type Experimental We experiment by attacking defended and undefended classifiers with Re Color Adv, by itself and in combination with other attacks. We find that Re Color Adv is a strong attack, reducing the accuracy of a Res Net-32 trained on CIFAR-10 to 3.0%.
Researcher Affiliation Academia Cassidy Laidlaw University of Maryland claidlaw@umd.edu Soheil Feizi University of Maryland sfeizi@cs.umd.edu
Pseudocode No The paper describes the methods and optimization process using textual descriptions and mathematical formulations, but it does not include structured pseudocode or algorithm blocks.
Open Source Code Yes We release our code at https://github.com/cassidylaidlaw/Re Color Adv.
Open Datasets Yes We evaluate Re Color Adv against defended and undefended neural networks on CIFAR-10 [13] and Image Net [20].
Dataset Splits No The paper uses standard datasets like CIFAR-10 and Image Net but does not explicitly state the training, validation, or test split percentages or sample counts in the main text.
Hardware Specification Yes All experiments were run on NVIDIA V100 GPUs.
Software Dependencies No The paper mentions using 'PyTorch [19]' and 'Adam optimizer [12]' but does not provide specific version numbers for these software dependencies.
Experiment Setup Yes We use the standard Adam optimizer [12] with a learning rate of 0.001.