AI Paper Atlas

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

Yet Another Intermediate-Level Attack

Qizhang Li, Yiwen Guo, Hao Chen

ECCV 2020 · Adversarial robustness and security › Black-box and transfer attacks · approach: Transferable adversarial examples · 36 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
use ILA++ (all intermediate discrepancies) instead of ILAI-FGSM · ImageNet (eps=0.03)average black-box success rate: 56.45 -> 60.42Improved
use ILA++ instead of ILAI-FGSM · CIFAR-100 (eps=0.03)average black-box success rate: 77.49 -> 79.38Improved
use ILA++ instead of ILAI-FGSM · ImageNet (eps=0.1)average black-box success rate: 94.89 -> 95.08No clear effect
use ILA++ instead of ILATAP · ImageNet (eps=0.03)average black-box success rate: 62.93 -> 64.21Improved
use ILA++ instead of ILAPGD · ImageNet (eps=0.03)average black-box success rate: 57.64 -> 60.79Improved
use ILA++ instead of ILAMI-FGSM · ImageNet (eps=0.03)average black-box success rate: 54.36 -> 57.54Improved
add intermediate-level normalization (ablation)ILA++ · CIFAR-100 (VGG-19 to WRN)success rate: 85.27 -> 85.53Improved
set lambda to 10 instead of infinity (ablation)ILA++ · CIFAR-100 (eps=0.03)average black-box success rate: 79.38 -> 79.55No clear effect
use earlier I-FGSM step (p=10) instead of p=100 as guides (ablation)ILA and ILA++ · CIFAR-100 (VGG-19, WRN)success rateImproved
ensemble I-FGSM and PGD discrepancies (ablation)ILA++ · ImageNet (eps=0.03)average black-box success rate: 60.42 -> 62.82Improved
use ILA++ instead of ILAI-FGSM · CIFAR-100 (l2)average black-box success rate: 73.73 -> 75.78Improved
use ILA++ instead of ILAI-FGSM · ImageNet (l2)average black-box success rate: 74.68 -> 76.73Improved

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