AI Paper Atlas

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

The Double-Edged Nature of the Rashomon Set for Trustworthy Machine Learning

Ethan Hsu, Harry Chen, Chudi Zhong, Lesia Semenova

ICML 2026 · Adversarial robustness and security › Attacks on text and graphs · approach: Membership inference and inversion · 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
select farthest-in-Hamming-distance trees instead of closestRashomon tree release · DRAFT reconstruction attackreconstruction errorHurt
increase number of released diverse treesRashomon tree ensembles · COMPAS and other datasetsadversarial accuracyImproved
increase number of released diverse treesRashomon tree ensembles · COMPAS and other datasetsreconstruction errorHurt
increase distance from the optimal treeRashomon set trees · adversarial datasetadversarial accuracyImproved
modify 6% of dataset and recompute Rashomon setRashomon set · four datasetsmodel overlap: more than 80% of models remainNo clear effect
modify 2% of dataset and recompute Rashomon setRashomon set · four datasetsmodel overlap: nearly identicalNo clear effect
increase attack strength to eta=l+I-1 on a single rule listsingle rule list · binary datasetsadversarial loss gapHurt

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