AI Paper Atlas

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

FAME: $\underline{F}$ormal $\underline{A}$bstract $\underline{M}$inimal $\underline{E}$xplanation for neural networks

Ryma Boumazouza, Raya Elsaleh, Melanie Ducoffe, Shahaf Bassan, Guy Katz

ICLR 2026 · Adversarial robustness and security › Certified and empirical robustness · approach: Decision-boundary geometry of robustness

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 greedy instead of MILP for abstract batch freeing (single round)FAME · MNIST/GTSRB modelsruntime: 9x to 12x speedupImproved
use greedy instead of MILP for abstract batch freeing (iterative refinement)FAME · GTSRB-CNNruntime: up to 2.4x speedupImproved
add iterative refinement of the perturbation domain to single-round FAME (ablation)FAME · MNIST-CNNexplanation size: 190.29 -> 122.09Improved
add iterative refinement of the perturbation domain to single-round FAME (ablation)FAME · GTSRB-CNNexplanation size: 379.34 -> 322.42Improved
use FAME-accelerated VERIX+ instead of VERIX+ aloneVERIX+ · GTSRB-CNNruntime (s): 185.03 -> 138.12Improved
use FAME-accelerated VERIX+ instead of VERIX+ aloneVERIX+ · MNIST-FCexplanation size: 280.16 -> 224.41Improved
use FAME iterative greedy non-minimal set instead of VERIX+ minimal setVERIX+ · GTSRB-CNNruntime: 338.28 features in 185.03s -> 322.42 features in 7.4sImproved
add cardinality-constrained perturbation domain (ablation)FAME · MNIST/GTSRB modelsexplanation sizeImproved
use FAME single-round on GTSRB-FC instead of VERIX+VERIX+ · GTSRB-FCexplanation size: 313.42 -> 243.18Improved

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