AI Paper Atlas

Research map / Label-efficient and robust learning / OOD and anomaly detection

LAMDA: A Longitudinal Android Malware Benchmark for Concept Drift Analysis

Md Ahsanul Haque, Ismail Hossain, Md Mahmuduzzaman Kamol, Md Jahangir Alam, Suresh kumar Amalapuram, Sajedul Talukder, Mohammad Saidur Rahman

ICLR 2026 · Label-efficient and robust learning › OOD and anomaly detection · approach: Uncertainty and misclassification detection · 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
evaluate on NEAR years instead of IID held-out monthLightGBM on LAMDA · LAMDAF1 (%): 97.49 -> 59.48Hurt
evaluate on FAR years instead of IID held-out monthLightGBM on LAMDA · LAMDAF1 (%): 97.49 -> 47.24Hurt
evaluate on FAR years instead of IID held-out monthLightGBM on LAMDA · LAMDAFNR (%): 1.74 -> 64.10Hurt
evaluate on FAR years instead of IIDLightGBM on LAMDA · LAMDAFPR (%): 2.69 -> 1.30No clear effect
evaluate on NEAR instead of IIDLightGBM on API Graph · API GraphF1 (%): 85.95 -> 66.77Hurt
evaluate on FAR instead of NEARLightGBM on API Graph · API GraphF1 (%): 66.77 -> 68.20No clear effect
use LAMDA instead of API Graph (stronger drift)LightGBM, FAR split · FARF1 (%): 68.20 -> 47.24Hurt
raise variance threshold from 0.001 to 0.01 (ablation)SVM on LAMDA NEAR · LAMDA NEARFPR (%): 4.07 -> 17.09Hurt
raise variance threshold from 0.001 to 0.01 (ablation)SVM on LAMDA NEAR · LAMDA NEARFNR (%): 55.62 -> 46.22Improved
raise variance threshold from 0.001 to 0.01 (ablation)LightGBM on LAMDA NEAR · LAMDA NEARprecision (%): 90.36 -> 75.03Hurt
raise variance threshold from 0.001 to 0.01 (ablation)LightGBM on LAMDA NEAR · LAMDA NEARF1 (%): 59.48 -> 61.38Improved

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