RISS 학술연구정보서비스

검색

인기 검색어

    다국어 입력

    http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.

    변환된 중국어를 복사하여 사용하시면 됩니다.

    예시)
    • 中文 을 입력하시려면 zhongwen을 입력하시고 space를누르시면됩니다.
    • 北京 을 입력하시려면 beijing을 입력하시고 space를 누르시면 됩니다.
    닫기
    KCI등재

    Sharpness-Aware Minimization을 적용한 Separable Vision Transformer 기반 악성코드 유형 분류 기법 = A Study on Malware Family Classification Method based on Separable Vision Transformer Using Sharpness-Aware Minimization

    한글로보기

    https://www.riss.kr/link?id=A109207611

    • 0

      상세조회
    • 0

      다운로드
    서지정보 열기
    • 내보내기
    • 내책장담기
    • 공유하기
      • URL 복사
    • 오류접수
    인용문이 복사되었습니다.

    부가정보

    다국어 초록 (Multilingual Abstract) kakao i 다국어 번역

    "The methods of classifying malware family through malware visualization generate malware images and then classify malware family using artificial intelligence models such as Convolutional Neural Networks(CNNs). However, such methods are vulnerable to malware obfuscation techniques. In this paper, we propose a malware classification method based on the Separable Vision Transformer(SepViT) that is robust against obfuscation techniques. The proposed method performs malware family classification using a SepViT model enhanced with Sharpness-Aware Minimization(SAM) after visualizing malware as grayscale images. From the experimental results using the Microsoft Malware Classification Challenge dataset, we show that SAM Optimizer-based SepViT used in the proposed method can classify malware family more accurately than four methods(ResNet18, ViT, CrossViT, SepViT). We also analyze the basis for classification of the proposed method using Grad-Cam. In addition, from the experiments using AndroDex dataset, we show that the proposed method shows good detection performance even in the presence of obfuscation in malware."
    번역하기

    "The methods of classifying malware family through malware visualization generate malware images and then classify malware family using artificial intelligence models such as Convolutional Neural Networks(CNNs). However, such methods are vulnerable to...

    "The methods of classifying malware family through malware visualization generate malware images and then classify malware family using artificial intelligence models such as Convolutional Neural Networks(CNNs). However, such methods are vulnerable to malware obfuscation techniques. In this paper, we propose a malware classification method based on the Separable Vision Transformer(SepViT) that is robust against obfuscation techniques. The proposed method performs malware family classification using a SepViT model enhanced with Sharpness-Aware Minimization(SAM) after visualizing malware as grayscale images. From the experimental results using the Microsoft Malware Classification Challenge dataset, we show that SAM Optimizer-based SepViT used in the proposed method can classify malware family more accurately than four methods(ResNet18, ViT, CrossViT, SepViT). We also analyze the basis for classification of the proposed method using Grad-Cam. In addition, from the experiments using AndroDex dataset, we show that the proposed method shows good detection performance even in the presence of obfuscation in malware."

    더보기

    참고문헌 (Reference)

    1 Chen, Xiangning, "When vision transformers outperform resnets without pre-training or strong data augmentations"

    2 Gibert, Daniel, "Using convolutional neural networks for classification of malware represented as images" 15 : 15-28, 2019

    3 Rong, Candong, "Umvd-fsl : Unseen malware variants detection using few-shot learning" 1-8, 2021

    4 Foret, Pierre, "Sharpness-aware minimization for efficiently improving generalization"

    5 Li, Wei, "Sepvit : Separable vision transformer"

    6 Battaglia, Peter, "Relational inductive biases, deep learning, and graph networks"

    7 Ronen, Royi, "Microsoft malware classification challenge"

    8 Nataraj, Lakshmanan, "Malware images : visualization and automatic classification" 1-7, 2011

    9 Lad, Sumit S, "Malware classification with improved convolutional neural network model" 12 (12): 30-43, 2020

    10 I. You, "Malware Obfuscation Techniques : A Brief Survey" 297-300, 2010

    1 Chen, Xiangning, "When vision transformers outperform resnets without pre-training or strong data augmentations"

    2 Gibert, Daniel, "Using convolutional neural networks for classification of malware represented as images" 15 : 15-28, 2019

    3 Rong, Candong, "Umvd-fsl : Unseen malware variants detection using few-shot learning" 1-8, 2021

    4 Foret, Pierre, "Sharpness-aware minimization for efficiently improving generalization"

    5 Li, Wei, "Sepvit : Separable vision transformer"

    6 Battaglia, Peter, "Relational inductive biases, deep learning, and graph networks"

    7 Ronen, Royi, "Microsoft malware classification challenge"

    8 Nataraj, Lakshmanan, "Malware images : visualization and automatic classification" 1-7, 2011

    9 Lad, Sumit S, "Malware classification with improved convolutional neural network model" 12 (12): 30-43, 2020

    10 I. You, "Malware Obfuscation Techniques : A Brief Survey" 297-300, 2010

    11 Xiao, Guoqing, "MalFCS : An effective malware classification framework with automated feature extraction based on deep convolutional neural networks" 141 : 49-58, 2020

    12 Rieck, K., "Learning and classification of malware behavior" Springer Berlin Heidelberg 108-125, 2008

    13 Bottou, "Large-scale machine learning with stochastic gradient descent" Physica- Verlag HD 177-186, 2010

    14 Guerra-Manzanares, Alejandro, "Kronodroid : Time-based hybrid-featured dataset for effective android malware detection and characterization" 110 : 102399-, 2021

    15 Obaidat, Islam, "Jadeite : A novel image-behaviorbased approach for java malware detection using deep learning" 113 : 102547-, 2022

    16 Vasan, Danish, "IMCFN : Image-based malware classification using fine-tuned convolutional neural network architecture" 171 : 107138-, 2020

    17 Selvaraju, Ramprasaath R, "Grad-cam : Visual explanations from deep networks via gradient-based localization" 618-626, 2017

    18 Arp, Daniel, "Drebin: Effective and explainable detection of android malware in your pocket" 14 : 23-26, 2014

    19 He, Kaiming, "Deep residual learning for image recognition" 770-778, 2016

    20 Chen, "Crossvit : Cross-attention multi-scale vision transformer for image classification" 357-366, 2021

    21 Allix, Kevin, "Androzoo : Collecting millions of android apps for the research community" 468-471, 2016

    22 Zhang, Wenhui, "Android malware detection using tcn with bytecode image" 13 (13): 1107-, 2021

    23 Aurangzeb, Sana, "AndroDex : Android Dex images of obfuscated malware" 11 (11): 212-, 2024

    24 AhnLab SEcurity intelligence Center(ASEC), "Andariel Group (MeshAgent) Attacking Using Domestic Asset Management Solutions"

    25 Dosovitskiy, Alexey, "An image is worth 16x16words : Transformers for image recognition at scale"

    26 Kingma, Diederik P, "Adam : A method for stochastic optimization"

    27 Park, Kyoung-Won, "A vision transformer enhanced with patch encoding for malware classification" Springer International Publishing 289-299, 2022

    더보기

    동일학술지(권/호) 다른 논문

    분석정보

    View

    상세정보조회

    0

    Usage

    원문다운로드

    0

    대출신청

    0

    복사신청

    0

    EDDS신청

    0

    동일 주제 내 활용도 TOP

    더보기

    주제

    연도별 연구동향

    연도별 활용동향

    연관논문

    연구자 네트워크맵

    공동연구자 (7)

    유사연구자 (20) 활용도상위20명

    해외이동버튼