AI Paper Atlas

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

Provably robust boosted decision stumps and trees against adversarial attacks

Maksym Andriushchenko, Matthias Hein

NeurIPS 2019 · Adversarial robustness and security › Certified and empirical robustness · approach: Provable robust learning guarantees · 37 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
Train boosted stumps by minimizing the exact robust loss rather than using standard trainingBoosted decision stumps · breast-cancer (ε∞=0.3)RTE (%): 98.5 -> 10.9Improved
Train boosted stumps with the robust-loss bound rather than standard trainingBoosted decision stumps · MNIST 2-6 (ε∞=0.3)RTE (%): 99.9 -> 9.1Improved
Use robust-loss-bound stump training instead of Robust stumps [cite]Boosted decision stumps · diabetes (ε∞=0.05)RTE (%): 30.5 -> 33.1Hurt
Use robust-loss-bound stump training instead of Robust stumps [cite]Boosted decision stumps · Results across eight binary datasetsRTE (%)Mixed
Train boosted trees by minimizing the upper bound on robust loss rather than using standard trainingBoosted decision trees · breast-cancer (ε∞=0.3)RTE (%): 81.0 -> 6.6Improved
Use robust-loss-bound tree training instead of Robust trees [cite]Boosted decision trees · Results across eight binary datasetsRTE (%)Improved
Use robust-loss-bound tree training rather than adversarial trainingBoosted decision trees · GTS 30-70 (ε∞=8/255)RTE (%): 26.7 -> 20.9Improved
Increase weak-learner expressiveness from stumps to depth-4 treesRobust boosted models · breast-cancer (ε∞=0.3)RTE (%): 10.9 -> 6.6Improved
Use the tree-wise upper bound on robust test error rather than exact MIP evaluationOur robust boosted trees · Results across binary datasetsRTE (%)No clear effect
Train stumps by optimizing the exact robust loss rather than its stump-wise bound (ablation)Our robust boosted stumps · RTE across eight binary datasetsRTE (%)No clear effect
Use robust-loss-bound stump training instead of exact robust-loss stump training (ablation)Our robust boosted stumps · MNIST 1-5 (ε∞=0.3)RTE (%): 3.6 -> 3.7Hurt
Increase perturbation radius ε during robust training (ablation)Robust boosted trees · Robustness–accuracy tradeofftest errorMixed

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