AI Paper Atlas

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

MultiGuard: Provably Robust Multi-label Classification against Adversarial Examples

Jinyuan Jia, Wenjie Qu, Neil Zhenqiang Gong

NeurIPS 2022 · Adversarial robustness and security › Certified and empirical robustness · approach: Provable defenses and their limits · 4 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
include the second terms in the certification inequality (ablation)MultiGuard · VOC 2007, R=0.5certified top-k precision@R: 23.6 -> 31.3Improved
include the second terms in the certification inequality (ablation)MultiGuard · VOC 2007, R=0.5certified top-k recall@R: 48.8 -> 66.4Improved
include the second terms in the certification inequality (ablation)MultiGuard · VOC 2007, R=0.5certified top-k f1-score@R: 31.8 -> 42.6Improved
joint certification over all ground-truth labels instead of per-label (Jia et al.)MultiGuard · VOC 2007certified precision/recall/f1@RImproved
increase k' (labels predicted by base classifier)MultiGuard · VOC 2007certified precision@RMixed
increase k (labels predicted by smoothed classifier)MultiGuard · VOC 2007certified precision@RMixed
increase kMultiGuard · VOC 2007certified recall@RImproved
increase noise sigmaMultiGuard · VOC 2007certified precision/recall/f1@RMixed
increase number of noisy samples nMultiGuard · VOC 2007certified precision/recall/f1@RImproved
increase alphaMultiGuard · VOC 2007certified precision/recall/f1@RNo clear effect

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