Mi-maml: classifying few-shot advanced malware using multi-improved model-agnostic meta-learning

被引:0
作者
Ji, Yulong [1 ]
Zou, Kunjin [2 ]
Zou, Bin [3 ]
机构
[1] Hubei Univ, Sch Cyber Sci & Technol, Wuhan 430062, Peoples R China
[2] Hubei Univ, Manchester Metropolitan Joint Inst, Wuhan 430062, Peoples R China
[3] Hubei Univ, Sch Math & Stat, Hubei Key Lab Appl Math, Wuhan 430062, Peoples R China
来源
CYBERSECURITY | 2024年 / 7卷 / 01期
关键词
Malware classification; Few-shot learning; Meta-learning; Data augmentation; PERFORMANCE;
D O I
10.1186/s42400-024-00314-9
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Malware classification has been successful in utilizing machine learning methods. However, it is limited by the reliance on a large number of high-quality labeled datasets and the issue of overfitting. These limitations hinder the accurate classification of advanced malware with only a few samples available. Meta-learning methods offer a solution by allowing models to quickly adapt to new tasks, even with a small number of samples. However, the effectiveness of meta-learning approaches in malware classification varies due to the diverse nature of malware types. Most meta-learning-based methodologies for malware classification either focus solely on data augmentation or utilize existing neural networks and learning rate schedules to adapt to the meta-learning model. These approaches do not consider the integration of both processes or tailor the neural network and learning rate schedules to the specific task. As a result, the classification performance and generalization capabilities are suboptimal. In this paper, we propose a multi-improved model-agnostic meta-learning (MI-MAML) model that aims to address the challenges encountered in few-shot malware classification. Specifically, we propose two data augmentation techniques to improve the classification performance of few-shot malware. These techniques involve utilizing grayscale images and the Lab color space. Additionally, we customize neural network architectures and learning rate schemes based on the representative few-shot classification method, MAML, to further enhance the model's classification performance and generalization ability for the task of few-shot malware classification. The results obtained from multiple few-shot malware datasets demonstrate that MI-MAML outperforms other models in terms of categorical accuracy, precision, and f1-score. Furthermore, we have conducted ablation experiments to validate the effectiveness of each stage of our work.
引用
收藏
页数:19
相关论文
共 50 条
  • [21] DOMAIN-AGNOSTIC META-LEARNING FOR CROSS-DOMAIN FEW-SHOT CLASSIFICATION
    Lee, Wei-Yu
    Wang, Jheng-Yu
    Wang, Yu-Chiang Frank
    2022 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2022, : 1715 - 1719
  • [22] Multi-scale Relation Network for Few-Shot Learning Based on Meta-learning
    Ding, Yueming
    Tian, Xia
    Yin, Lirong
    Chen, Xiaobing
    Liu, Shan
    Yang, Bo
    Zheng, Wenfeng
    COMPUTER VISION SYSTEMS (ICVS 2019), 2019, 11754 : 343 - 352
  • [23] Theoretical Convergence of Multi-Step Model-Agnostic Meta-Learning
    Ji, Kaiyi
    Yang, Junjie
    Liang, Yingbin
    JOURNAL OF MACHINE LEARNING RESEARCH, 2022, 23
  • [24] A Study on Position Control of a Continuum Arm Using MAML (Model-Agnostic Meta-Learning) for Adapting Different Loading Conditions
    Sahoo, Alok Ranjan
    Chakraborty, Pavan
    IEEE ACCESS, 2022, 10 : 14980 - 14992
  • [25] IMAL: An Improved Meta-learning Approach for Few-shot Classification of Plant Diseases
    Wang, Yingtao
    Wang, Shunfang
    2021 IEEE 21ST INTERNATIONAL CONFERENCE ON BIOINFORMATICS AND BIOENGINEERING (IEEE BIBE 2021), 2021,
  • [26] Can we improve meta-learning model in few-shot learning by aligning data distributions?
    Tian, Pinzhuo
    Yu, Hang
    KNOWLEDGE-BASED SYSTEMS, 2023, 277
  • [27] Few-shot short utterance speaker verification using meta-learning
    Wang W.
    Zhao H.
    Yang Y.
    Chang Y.
    You H.
    PeerJ Computer Science, 2023, 9
  • [28] MAML-KalmanNet: A Neural Network-Assisted Kalman Filter Based on Model-Agnostic Meta-Learning
    Chen, Shanli
    Zheng, Yunfei
    Lin, Dongyuan
    Cai, Peng
    Xiao, Yingying
    Wang, Shiyuan
    IEEE TRANSACTIONS ON SIGNAL PROCESSING, 2025, 73 : 988 - 1003
  • [29] Few-shot short utterance speaker verification using meta-learning
    Wang, Weijie
    Zhao, Hong
    Yang, Yikun
    Chang, YouKang
    You, Haojie
    PEERJ COMPUTER SCIENCE, 2023, 9
  • [30] Few-Shot Deep Model of Waste classification Based on Model Agnostic Meta Learning
    Feng, Bo
    Ren, Kun
    Tao, Qingyang
    Han, Honggui
    OPTOELECTRONIC IMAGING AND MULTIMEDIA TECHNOLOGY VIII, 2021, 11897