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
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 |
|---|---|---|---|
| Encode API arguments alongside API names and categories | Dynamic malware detection models · May test | AUC: about 1% | Improved |
| Use heterogeneous feature hashing for API names, categories, and arguments with gated CNNs and a Bi-LSTM | Proposed Model · May test | AUC: 98.19±0.32 -> 98.71±0.17 | Improved |
| Use kernel-size-2-and-3 Gated CNNs rather than only kernel-size-2 (ablation) | Proposed Model · Ablation experiments | AUC: 98.80% -> 98.86% | Improved |
| Add a kernel-size-4 Gated CNN to the kernel-size-2-and-3 configuration (ablation) | Proposed Model · Ablation experiments | AUC | No clear effect |
| Add the Bi-LSTM (ablation) | Proposed Model · Ablation experiments | AUC | Improved |
| Use one Bi-LSTM rather than two stacked Bi-LSTMs (ablation) | Proposed Model · Ablation experiments | AUC: 98.80% | Improved |
| Use one Bi-LSTM rather than two stacked Bi-LSTMs (ablation) | Proposed Model · Ablation experiments | Computation time: 2 times faster | Improved |
| Use both batch-normalization layers rather than omitting one or both (ablation) | Proposed Model · Ablation experiments | AUC: 98.80% | Improved |
Closest papers by meaning
- Classifying Sequences of Extreme Length with Constant Memory Applied to Malware Detection (AAAI 2021 · similarity 0.84)
- Feature-Space Bayesian Adversarial Learning Improved Malware Detector Robustness (AAAI 2023 · similarity 0.83)
- MalCL: Leveraging GAN-Based Generative Replay to Combat Catastrophic Forgetting in Malware Classification (AAAI 2025 · similarity 0.82)
- DRSM: De-Randomized Smoothing on Malware Classifier Providing Certified Robustness (ICLR 2024 · similarity 0.81)
- MalDetectFormer: Leveraging Sparse SpatioTemporal Information for Effective Malicious Traffic Detection (AAAI 2025 · similarity 0.80)
- VLMGuard: Bootstrapping Malicious Prompt Detectors from Unlabeled Vision-Language Prompts in the Wild (NeurIPS 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.
