Summary of Morph: Towards Automated Concept Drift Adaptation For Malware Detection, by Md Tanvirul Alam et al.
MORPH: Towards Automated Concept Drift Adaptation for Malware Detection
by Md Tanvirul Alam, Romy Fieblinger, Ashim Mahara, Nidhi Rastogi
First submitted to arxiv on: 23 Jan 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: None
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The proposed MORPH method is a pseudo-label-based concept drift adaptation technique designed to mitigate the performance degradation of trained neural networks in malware detection tasks. By retraining the model using pseudo labels, MORPH adapts to shifting data distributions and reduces annotation efforts when combined with active learning. Experimental results on Android and Windows malware datasets demonstrate the efficacy of MORPH in mitigating the impact of concept drift, outperforming existing works in automated concept drift adaptation. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary MORPH is a new way to make machine learning models better at detecting malware over time. Right now, malware detection models get worse as new types of malware are created. This makes them not very useful for catching new malware. MORPH helps by retraining the model using fake labels that are similar to real labels. This makes the model better at catching new malware without needing a lot more data or human help. |
Keywords
* Artificial intelligence * Active learning * Machine learning
