AI Paper Atlas

Research map / Adversarial robustness and security / Black-box and transfer attacks

Practical Black-box Attacks on Deep Neural Networks using Efficient Query Mechanisms

Arjun Nitin Bhagoji, Warren He, Bo Li, Dawn Song

ECCV 2018 · Adversarial robustness and security › Black-box and transfer attacks · approach: Query-efficient black-box attacks · 236 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add random grouping (RG-8) query reduction to iterative FD attack (ablation)IFD-logit, Model A · MNIST targeted (eps=0.3)targeted attack success rate (%): 99.7 -> 73.8Hurt
add random grouping (RG-8) query reduction to iterative FD attack (ablation)IFD-logit, Resnet-32 · CIFAR-10 targeted (eps=8)targeted attack success rate (%): 100.0 -> 97.0Mixed
use PCA-100 instead of random grouping for single-step query reduction (ablation)Gradient Estimation, Model A · MNIST targeted (eps=0.3) single-steptargeted attack success rate (%): 15.9 -> 23.2Improved
use PCA-100 instead of random grouping for iterative query reduction (ablation)Gradient Estimation, Model A · MNIST targeted (eps=0.3)targeted attack success rate (%): 73.8 -> 96.2Improved
use iterative instead of single-step finite-difference attackFD-logit, Model A · MNIST targeted (eps=0.3)targeted attack success rate (%): 29.9 -> 99.7Improved
add random grouping (RG-8) to single-step finite-difference attack (ablation)Finite Diff., Model A · MNIST untargeted (eps=0.3)attack success rate (%): 92.9 -> 61.5Hurt
use iterative Gradient Estimation RG-8 instead of SPSAGradient Estimation, Model A · MNIST untargeted (eps=0.3)attack success rate (%): 96.7 -> 98.4Improved
use iterative Gradient Estimation RG-8 instead of SPSAGradient Estimation, Resnet-32 · CIFAR-10 untargeted (eps=8)attack success rate (%): 88.0 -> 99.0Improved
use Particle Swarm Optimization instead of single-step Finite Diff.PSO, Model A · MNIST untargeted (eps=0.3)attack success rate (%): 92.9 -> 84.1Hurt
train target with iterative adversarial training instead of FGS adversarial trainingIFD-logit, Model A · MNIST untargeted (eps=0.3)untargeted attack success rate (%): 76.5 -> 11.6Hurt
train target with iterative adversarial training instead of FGS adversarial trainingIFD-logit, Resnet-32 · CIFAR-10 adversarially trained (eps=8)untargeted attack success rate (%): 100.0 -> 54.6Hurt
round output probabilities to two decimal places as countermeasure (ablation)Gradient Estimation attacks · MNIST/CIFAR-10 undefendedattack success rate (%): 28.0%Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy