AVA: Adversarial Vignetting Attack against Visual Recognition

Authors: Binyu Tian, Felix Juefei-Xu, Qing Guo, Xiaofei Xie, Xiaohong Li, Yang Liu

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

Reproducibility Variable Result LLM Response
Research Type Experimental We validate the proposed methods on three popular datasets, i.e., DEV, CIFAR10, and Tiny Image Net, by attacking four CNNs, e.g., Res Net50, Efficient Net-B0, Dense Net121, and Mobile Net-V2, demonstrating the advantages of our methods over baseline methods on both transferability and image quality.
Researcher Affiliation Collaboration Binyu Tian1 , Felix Juefei-Xu2 , Qing Guo3 , Xiaofei Xie3 , Xiaohong Li1 , Yang Liu3 1 College of Intelligence and Computing, Tianjin University, China 2 Alibaba Group, USA 3 Nanyang Technological University, Singapore
Pseudocode Yes We summarize the workflow of our attacking algorithm in the following steps: Initialize the parameters P = {f 1, α, τ, χ} = {1, 0, 0, 0}, the geometry vignetting matrix G as 1 αR, and the distance matrix R via R[i] = p u2 i + v2 i . Calculate the illumination-related matrix A via Eq. (2), and the camera tilting-related matrix T via Eq (4). At the t-th iteration, calculate the gradient of Gt, Pt with respect to the objective function Eq. (8) and obtain Gt and { ρt|ρt Pt}. Update Gt and Pt with their own step sizes. Update t = t + 1 and go to the step three for further optimization until it reaches the maximum iteration or vig(I, P) fools the DNN.
Open Source Code No The paper does not provide an explicit statement about open-sourcing the code for the described methodology or a link to a code repository.
Open Datasets Yes We carry out our experiments on three popular datasets, i.e., DEV [Google, 2017], CIFAR10 [Krizhevsky and Hinton, 2009], and Tiny Image Net [Stanford, 2017].
Dataset Splits Yes We train these models on the CIFAR10 and Tiny Image Net dataset. For DEV dataset, we use the pretrained models.
Hardware Specification No The paper does not explicitly describe the specific hardware (e.g., GPU models, CPU types) used to run its experiments.
Software Dependencies No The paper mentions the use of 'state-of-the-art deep convolutional neural networks (CNNs)' and specific models like 'Res Net50, Efficient Net-B0, Dense Net121, and Mobile Net-V2', but does not provide specific version numbers for any software dependencies.
Experiment Setup Yes In the experimental parts, we set our hyper-parameters as follows: we set the stepsize of f, α, τ, χ and Gt as 0.0125, 0.0125, 0.01, 0.01 and 0.0125, respectively. We set the number of iterations to be 40 and z of the level-set method to be 1.0. We set p to be , and set the ϵ of f 1, α, τ, and χ as 0.5, 0.5, π/6, and π/6. In addition, we set λf, λg and λα all to be 1.