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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| evaluate on NEAR years instead of IID held-out month | LightGBM on LAMDA · LAMDA | F1 (%): 97.49 -> 59.48 | Hurt |
| evaluate on FAR years instead of IID held-out month | LightGBM on LAMDA · LAMDA | F1 (%): 97.49 -> 47.24 | Hurt |
| evaluate on FAR years instead of IID held-out month | LightGBM on LAMDA · LAMDA | FNR (%): 1.74 -> 64.10 | Hurt |
| evaluate on FAR years instead of IID | LightGBM on LAMDA · LAMDA | FPR (%): 2.69 -> 1.30 | No clear effect |
| evaluate on NEAR instead of IID | LightGBM on API Graph · API Graph | F1 (%): 85.95 -> 66.77 | Hurt |
| evaluate on FAR instead of NEAR | LightGBM on API Graph · API Graph | F1 (%): 66.77 -> 68.20 | No clear effect |
| use LAMDA instead of API Graph (stronger drift) | LightGBM, FAR split · FAR | F1 (%): 68.20 -> 47.24 | Hurt |
| raise variance threshold from 0.001 to 0.01 (ablation) | SVM on LAMDA NEAR · LAMDA NEAR | FPR (%): 4.07 -> 17.09 | Hurt |
| raise variance threshold from 0.001 to 0.01 (ablation) | SVM on LAMDA NEAR · LAMDA NEAR | FNR (%): 55.62 -> 46.22 | Improved |
| raise variance threshold from 0.001 to 0.01 (ablation) | LightGBM on LAMDA NEAR · LAMDA NEAR | precision (%): 90.36 -> 75.03 | Hurt |
| raise variance threshold from 0.001 to 0.01 (ablation) | LightGBM on LAMDA NEAR · LAMDA NEAR | F1 (%): 59.48 -> 61.38 | Improved |
Closest papers by meaning
- DRSM: De-Randomized Smoothing on Malware Classifier Providing Certified Robustness (ICLR 2024 · similarity 0.82)
- MalCL: Leveraging GAN-Based Generative Replay to Combat Catastrophic Forgetting in Malware Classification (AAAI 2025 · similarity 0.82)
- SRDC: Semantics-based Ransomware Detection and Classification with LLM-assisted Pre-training (AAAI 2025 · similarity 0.81)
- T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generation (CVPR 2025 · similarity 0.80)
- JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models (NeurIPS 2024 · similarity 0.80)
- MCA-Bench: A Multimodal Benchmark for Evaluating CAPTCHA Robustness Against VLM-based Attacks (AAAI 2026 · similarity 0.80)
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.
