AI Paper Atlas

Research map / Adversarial robustness and security / Certified and empirical robustness

Online Adversarial Attacks

Andjela Mladenovic, Joey Bose, Hugo Berard, William L. Hamilton, Simon Lacoste-Julien, Pascal Vincent, Gauthier Gidel

ICLR 2022 · Adversarial robustness and security › Certified and empirical robustness · approach: Regularized defenses against attacks · 0 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 an online selection algorithm instead of random selection (average aggregate improvement)Online adversarial attacks · MNIST and CIFAR-10online fool rate: 7.5% and 34.1%Improved
Use Virtual+ instead of Virtual or OptimisticOnline adversarial attacks · CIFAR-10, non-robust and robust classifiersonline fool rateImproved
Use Virtual+ instead of Virtual or OptimisticOnline adversarial attacks · Robust classifiers, except MNIST at k=10online fool rateImproved
Use Virtual+ instead of Single-RefOnline adversarial attacks · MNIST, k=1000online fool rate: 15.3%Improved
Use an online algorithm rather than Naive random selectionOnline adversarial attacks · ImageNet non-robust classifiersonline fool rateImproved
Use Virtual+ instead of the strongest single-threshold baselinesk-secretary algorithms · k=2, 3, and 4competitive ratio: C_2≥0.427, C_3≥ .457, C_4≥.4769Improved
Use Single-Ref instead of Virtual+k-secretary algorithms · 5≤k≤100competitive ratioHurt
Use FGSM rather than PGD with an online selection algorithmOnline adversarial attacks · Online blackbox transfer attacksonline fool rateMixed

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