AI Paper Atlas

Research map / Large language models / Agents, code and math

Improving Certified Robustness via Statistical Learning with Logical Reasoning

Zhuolin Yang, Zhikuan Zhao, Boxin Wang, Jiawei Zhang, Linyi Li, Hengzhi Pei, Bojan Karlaš, Ji Liu, Heng Guo, Ce Zhang, Bo Li

NeurIPS 2022 · Large language models › Agents, code and math · approach: Inductive and abstract reasoning evaluation · 6 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
add domain knowledge rules and MLN reasoning to randomized-smoothed sensing modelsGTSRB road-sign sensing pipeline · GTSRB road signs, ℓ2 perturbations CI=0.12, 0.25, 0.50, and 1.00certified accuracy: 90.8 -> 96.0; 88.4 -> 91.0; 73.2 -> 75.5; 61.7 -> 62.5Improved
add domain knowledge rules and MLN reasoningHighTech information-extraction pipeline · HighTech information extraction, CS=0.1certified accuracy: 99.7 -> 100.0Improved
add domain knowledge rules and MLN reasoningHighTech information-extraction pipeline · HighTech information extraction, CS=0.5certified accuracy: 94.7 -> 100.0Improved
add domain knowledge rules and MLN reasoningHighTech information-extraction pipeline · HighTech information extraction, CS=0.9certified accuracy: 38.4 -> 58.8Improved
add hierarchy and exclusion knowledge rulesPrimateNet sensing pipeline · PrimateNet benign test data, σ=0.12, 0.25, and 0.50accuracy: 0.9638 -> 0.9670; 0.9554 -> 0.9612; 0.9371 -> 0.9435Improved
add hierarchy and exclusion knowledge rulesPrimateNet sensing pipeline · PrimateNet, CI=0.12, α=10%, σ=0.12certified robustness: 0.5724 -> 0.8849Improved
add hierarchy and exclusion knowledge rulesPrimateNet sensing pipeline · PrimateNet, CI=0.50, α=50%, σ=0.50certified robustness: 0.4635 -> 0.5581Improved
use a knowledge-based sensing-reasoning pipeline rather than vanilla randomized smoothingGTSRB road-sign classification · CI=0.50 or 1.00 with σ=0.12certified accuracy: 0.0 -> 73.2; 0.0 -> 24.2Improved

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