AI Paper Atlas

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

Practical No-box Adversarial Attacks against DNNs

Qizhang Li, Yiwen Guo, Hao Chen

NeurIPS 2020 · Adversarial robustness and security › Black-box and transfer attacks · approach: Robustness benchmarks and defenses · 6 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
Replace conventional small-data supervised training with prototypical reconstructionNo-box substitute models · ImageNet, ε=0.1, average across victim modelsprediction accuracy on adversarial examples: 81.29% -> 33.94%Improved
Add multiple decoders to prototypical reconstruction (ablation)Prototypical no-box substitute · ImageNet, ε=0.1, average across victim modelsprediction accuracy on adversarial examples: 33.94% -> 31.26%Improved
Train with rotation reconstruction rather than conventional unsupervised autoencodingNo-box substitute models · ImageNet, ε=0.1, average across victim modelsprediction accuracy on adversarial examples: 57.78% -> 45.35%Improved
Train with jigsaw reconstruction rather than conventional unsupervised autoencodingNo-box substitute models · ImageNet, ε=0.1, average across victim modelsprediction accuracy on adversarial examples: 57.78% -> 46.04%Improved
Increase prototypical decoder count from 1 to 5 (ablation)Prototypical no-box substitute · ImageNet, ε=0.1, average across victim modelsprediction accuracy on adversarial examples: 33.94% -> 32.05%Improved
Increase prototypical decoder count from 5 to 10 (ablation)Prototypical no-box substitute · ImageNet, ε=0.1, average across victim modelsprediction accuracy on adversarial examples: 32.05% -> 31.50%Improved
Increase prototypical decoder count from 10 to 20 (ablation)Prototypical no-box substitute · ImageNet, ε=0.1, average across victim modelsprediction accuracy on adversarial examples: 31.50% -> 31.26%Improved
Use prototypical reconstruction rather than Beyonder transferNo-box attacks · ImageNet, ε=0.1, average across victim modelsprediction accuracy on adversarial examples: 36.26% -> 31.26%Improved
Use the no-box attack instead of Beyonder transferClarifai celebrity recognition · Clarifai, ε=0.1prediction accuracy on adversarial examples: 14.29% -> 15.40%Hurt
Use the no-box attack instead of Beyonder transferClarifai celebrity recognition · Clarifai, ε=0.08prediction accuracy on adversarial examples: 21.85% -> 33.67%Hurt
Apply proposed no-box adversarial examples rather than Naïve† examplesAdversarially trained ResNet · ImageNetaccuracy on adversarial examples: 54.12% -> 39.24%Improved
Increase the number of training images (ablation)Prototypical no-box substitutes · ImageNetprediction accuracy on adversarial examplesImproved

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