AI Paper Atlas

Research map / Adversarial robustness and security / Attacks on text and graphs

DisGUIDE: Disagreement-Guided Data-Free Model Extraction

Jonathan Rosenthal, Eric Enouen, Hung Viet Pham, Lin Tan

AAAI 2023 · Adversarial robustness and security › Attacks on text and graphs · approach: Membership inference and inversion · 21 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
Train two clones and guide the generator with their disagreement lossData-free model extraction · CIFAR-10 soft-labelclone accuracy (%): 91.24 -> 94.02 ± 0.25Improved
Train two clones and guide the generator with their disagreement lossData-free model extraction · CIFAR-10 hard-labelclone accuracy (%): 84.51 -> 87.93 ± 1.74Improved
Train two clones and guide the generator with their disagreement lossData-free model extraction · CIFAR-100 hard-labelclone accuracy (%): 43.56 -> 62.04 ± 1.03Improved
Use DisGUIDE rather than DFME to reach the reported accuracyCIFAR-10 soft-label extraction · DFME accuracy targetqueries: 20M -> 3.13M ± 0.57MImproved
Use DisGUIDE rather than DFMS to reach the reported accuracyCIFAR-10 soft-label extraction · DFMS accuracy targetqueries: 20M -> 7.01M ± 1.30MImproved
Use DisGUIDE rather than DFMS to reach the reported accuracyCIFAR-10 hard-label extraction · DFMS accuracy targetqueries: 8M -> 4.02M ± 1.43MImproved
Use DisGUIDE rather than DFMS to reach the reported accuracyCIFAR-100 hard-label extraction · DFMS accuracy targetqueries: 10M -> 3.87M ± 0.37MImproved
Convert a fraction of generated images to grayscale (ablation)DisGUIDE · CIFAR-10 soft-labelclone accuracy (%): 93.25 ± 0.15% -> 93.36 ± 0.16%No clear effect
Convert a fraction of generated images to grayscale (ablation)DisGUIDE · CIFAR-10 hard-labelclone accuracy (%): 85.54 ± 2.47% -> 87.93 ± 1.74%Improved
Increase replay buffer size from 0.05M to 1M (ablation)DisGUIDE · CIFAR-10 soft-labelclone accuracy (%): 93.06 -> 93.36No clear effect
Increase replay sampling frequency (ablation)DisGUIDE · CIFAR-10 soft-labelclone accuracy (%): 92.3 -> 93.7Improved
Increase replay sampling frequency (ablation)DisGUIDE · CIFAR-10 soft-labelruntime (hours): 7.0 -> 15.2Hurt

Later papers that compared with this method

1 later accepted paper reports DisGUIDE as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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