On-device Malware Detection using Performance-Aware and Robust Collaborative Learning

被引:21
|
作者
Shukla, Sanket [1 ]
Manoj, Sai P. D. [1 ]
Kolhe, Gaurav [2 ]
Rafatirad, Setareh [3 ]
机构
[1] George Mason Univ, Dept Elect & Comp Engn, Fairfax, VA 22030 USA
[2] Univ Calif Davis, Dept Elect & Comp Engn, Davis, CA 95616 USA
[3] Univ Calif Davis, Dept Comp Sci, Davis, CA 95616 USA
来源
2021 58TH ACM/IEEE DESIGN AUTOMATION CONFERENCE (DAC) | 2021年
关键词
D O I
10.1109/DAC18074.2021.9586330
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
The proliferation of the Internet-of-Things (IoT) devices has facilitated smart connectivity and enhanced computational capabilities. Lack of proper security protocols in such devices makes them vulnerable to cyber threats, especially malware attacks. Given the diversity and sophistication in malware samples, detecting them using traditional vendor database-based signature matching techniques is inefficient. This paper presents a collaborative machine learning (ML)-based malware detection framework. We introduce a) performance-aware precision-scaled federated learning (FL) to minimize the communication overheads with minimal device-level computations; and (2) a Robust and Active Protection with Intelligent Defense strategy against malicious activity (RAPID) at the device and network-level due to malware and other cyber-attacks. Deploying FL facilitates detecting malware attacks through collaborative learning and prevents data sharing, thus ensuring data security and privacy. RAPID denies the illegitimate user and aids in developing an effective collaborative malware detection model. A comprehensive analysis, results, and performance of the proposed technique are presented along with the communication overheads. An average accuracy of 94% is obtained with the proposed technique with 15% communication overhead, indicating 19% better performance than state-of-the-art techniques. Furthermore, the minimum accuracy drop of a model trained using RAPID is only 3% when 10% of devices are adversarial and 16% even when 40% of devices are adversarial.
引用
收藏
页码:967 / 972
页数:6
相关论文
共 50 条
  • [21] Android malware detection using time-aware machine learning approach
    Alsobeh, Anas M. R.
    Gaber, Khalid
    Hammad, Mahmoud M.
    Nuser, Maryam
    Shatnawi, Amani
    CLUSTER COMPUTING-THE JOURNAL OF NETWORKS SOFTWARE TOOLS AND APPLICATIONS, 2024, 27 (09): : 12627 - 12648
  • [22] RevMatch: An Efficient and Robust Decision Model for Collaborative Malware Detection
    Fung, Carol J.
    Lam, Disney Y.
    Boutaba, Raouf
    2014 IEEE NETWORK OPERATIONS AND MANAGEMENT SYMPOSIUM (NOMS), 2014,
  • [23] LightEQ: On-Device Earthquake Detection with Embedded Machine Learning
    Zainab, Tayyaba
    Karstens, Jens
    Landsiedel, Olaf
    PROCEEDINGS 8TH ACM/IEEE CONFERENCE ON INTERNET OF THINGS DESIGN AND IMPLEMENTATION, IOTDI 2023, 2023, : 130 - 143
  • [24] Generative Learning Plan Recommendation for Employees: A Performance-aware Reinforcement Learning Approach
    Zheng, Zhi
    Sun, Ying
    Song, Xin
    Zhu, Hengshu
    Xiong, Hui
    PROCEEDINGS OF THE 17TH ACM CONFERENCE ON RECOMMENDER SYSTEMS, RECSYS 2023, 2023, : 443 - 454
  • [25] Model-Agnostic Decentralized Collaborative Learning for On-Device POI Recommendation
    Long, Jing
    Chen, Tong
    Quoc Viet Hung Nguyen
    Xu, Guandong
    Zheng, Kai
    Yin, Hongzhi
    PROCEEDINGS OF THE 46TH INTERNATIONAL ACM SIGIR CONFERENCE ON RESEARCH AND DEVELOPMENT IN INFORMATION RETRIEVAL, SIGIR 2023, 2023, : 423 - 432
  • [26] Collaborative Learning Based Effective Malware Detection System
    Singh, Narendra
    Kasyap, Harsh
    Tripathy, Somanath
    ECML PKDD 2020 WORKSHOPS, 2020, 1323 : 205 - 219
  • [27] uPIM: Performance-aware Online Learning Capable Processing-in-Memory
    Bavikadi, Sathwika
    Sutradhar, Purab Ranjan
    Ganguly, Amlan
    Dinakarrao, Sai Manoj Pudukotai
    2021 IEEE 3RD INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE CIRCUITS AND SYSTEMS (AICAS), 2021,
  • [28] Performance-aware scheduling of streaming applications using genetic algorithm
    Smirnov, Pavel
    Melnik, Mikhail
    Nasonov, Denis
    INTERNATIONAL CONFERENCE ON COMPUTATIONAL SCIENCE (ICCS 2017), 2017, 108 : 2240 - 2249
  • [29] Topology Optimization of Operational Amplifiers Using A Performance-aware Representation
    Shen, Jinyi
    Yang, Fan
    Shang, Li
    Yan, Changhao
    Bi, Zhaori
    Zhou, Dian
    Zeng, Xuan
    2024 INTERNATIONAL SYMPOSIUM OF ELECTRONICS DESIGN AUTOMATION, ISEDA 2024, 2024, : 166 - 170
  • [30] Malware Detection using Malware Image and Deep Learning
    Choi, Sunoh
    Jang, Sungwook
    Kim, Youngsoo
    Kim, Jonghyun
    2017 INTERNATIONAL CONFERENCE ON INFORMATION AND COMMUNICATION TECHNOLOGY CONVERGENCE (ICTC), 2017, : 1193 - 1195