AI Paper Atlas

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

Reverse KL-Divergence Training of Prior Networks: Improved Uncertainty and Adversarial Robustness

Andrey Malinin, Mark Gales

NeurIPS 2019 · Adversarial robustness and security › Certified and empirical robustness · approach: Adversarial training recipes · 67 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 Prior Networks with the proposed reverse-KL criterion instead of standard adversarial trainingPrior Networks · Adversarial trainingadversarial robustnessImproved
Set the reverse-KL loss gamma to 10.0 rather than 1.0 (ablation)Reverse-KL Prior Networks · Other datasetsreverse-KL loss performanceImproved
Vary beta (ablation)Reverse-KL Prior Networks · Not specifiedmodel performanceNo clear effect
Set beta to 0 for OOD training data (ablation)Reverse-KL Prior Networks · OOD detectionseparation of in-domain and OOD uncertaintyImproved
Set beta to 1 for adversarial training data (ablation)Reverse-KL Prior Networks · Adversarial trainingjoint target-class prediction and uncertaintyImproved

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