AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Dynamic Malware Analysis with Feature Engineering and Feature Learning

Zhaoqi Zhang, Panpan Qi, Wei Wang

AAAI 2020 · Label-efficient and robust learning › Recognition and long-tail · approach: Dense features and foundation priors · 182 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
Encode API arguments alongside API names and categoriesDynamic malware detection models · May testAUC: about 1%Improved
Use heterogeneous feature hashing for API names, categories, and arguments with gated CNNs and a Bi-LSTMProposed Model · May testAUC: 98.19±0.32 -> 98.71±0.17Improved
Use kernel-size-2-and-3 Gated CNNs rather than only kernel-size-2 (ablation)Proposed Model · Ablation experimentsAUC: 98.80% -> 98.86%Improved
Add a kernel-size-4 Gated CNN to the kernel-size-2-and-3 configuration (ablation)Proposed Model · Ablation experimentsAUCNo clear effect
Add the Bi-LSTM (ablation)Proposed Model · Ablation experimentsAUCImproved
Use one Bi-LSTM rather than two stacked Bi-LSTMs (ablation)Proposed Model · Ablation experimentsAUC: 98.80%Improved
Use one Bi-LSTM rather than two stacked Bi-LSTMs (ablation)Proposed Model · Ablation experimentsComputation time: 2 times fasterImproved
Use both batch-normalization layers rather than omitting one or both (ablation)Proposed Model · Ablation experimentsAUC: 98.80%Improved

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