Segmentation Fault: A Cheap Defense Against Adversarial Machine Learning

被引:1
|
作者
Al Bared, Doha [1 ]
Nassar, Mohamed [2 ]
机构
[1] Amer Univ Beirut AUB, Dept Comp Sci, Beirut, Lebanon
[2] Univ New Haven, Dept Comp Sci, West Haven, CT USA
关键词
Machine Learning; Adversarial ML; Neural Networks; Computer Vision;
D O I
10.1109/MENACOMM50742.2021.9678308
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Recently published attacks against deep neural networks (DNNs) have stressed the importance of methodologies and tools to assess the security risks of using this technology in critical systems. Efficient techniques for detecting adversarial machine learning helps establishing trust and boost the adoption of deep learning in sensitive and security systems. In this paper, we propose a new technique for defending deep neural network classifiers, and convolutional ones in particular. Our defense is cheap in the sense that it requires less computation power despite a small cost to pay in terms of detection accuracy. The work refers to a recently published technique called ML-LOO. We replace the costly pixel by pixel leave-one-out approach of ML-LOO by adopting coarse-grained leave-one-out. We evaluate and compare the efficiency of different segmentation algorithms for this task. Our results show that a large gain in efficiency is possible, even though penalized by a marginal decrease in detection accuracy.
引用
收藏
页码:37 / 42
页数:6
相关论文
共 50 条
  • [1] A Moving Target Defense against Adversarial Machine Learning
    Roy, Abhishek
    Chhabra, Anshuman
    Kamhoua, Charles A.
    Mohapatra, Prasant
    SEC'19: PROCEEDINGS OF THE 4TH ACM/IEEE SYMPOSIUM ON EDGE COMPUTING, 2019, : 383 - 388
  • [2] A Network Security Classifier Defense: Against Adversarial Machine Learning Attacks
    De Lucia, Michael J.
    Cotton, Chase
    PROCEEDINGS OF THE 2ND ACM WORKSHOP ON WIRELESS SECURITY AND MACHINE LEARNING, WISEML 2020, 2020, : 67 - 73
  • [3] HyperAdv: Dynamic Defense Against Adversarial Radio Frequency Machine Learning Systems
    Zhang, Milin
    De Lucia, Michael
    Swami, Ananthram
    Ashdown, Jonathan
    Turck, Kurt
    Restuccia, Francesco
    MILCOM 2024-2024 IEEE MILITARY COMMUNICATIONS CONFERENCE, MILCOM, 2024, : 821 - 826
  • [4] Using Undervolting as an on-Device Defense Against Adversarial Machine Learning Attacks
    Majumdar, Saikat
    Samavatian, Mohammad Hossein
    Barber, Kristin
    Teodorescu, Radu
    2021 IEEE INTERNATIONAL SYMPOSIUM ON HARDWARE ORIENTED SECURITY AND TRUST (HOST), 2021, : 158 - 169
  • [5] A Survey on Adversarial Machine Learning for Cyberspace Defense
    Yu, Zheng-Fei
    Yan, Qiao
    Zhou, Yun
    Zidonghua Xuebao/Acta Automatica Sinica, 2022, 48 (07): : 1625 - 1649
  • [6] Defense strategies for Adversarial Machine Learning: A survey
    Bountakas, Panagiotis
    Zarras, Apostolis
    Lekidis, Alexios
    Xenakis, Christos
    COMPUTER SCIENCE REVIEW, 2023, 49
  • [7] Defense Against Adversarial Attacks in Deep Learning
    Li, Yuancheng
    Wang, Yimeng
    APPLIED SCIENCES-BASEL, 2019, 9 (01):
  • [8] AttriGuard: A Practical Defense Against Attribute Inference Attacks via Adversarial Machine Learning
    Jia, Jinyuan
    Gong, Neil Zhenqiang
    PROCEEDINGS OF THE 27TH USENIX SECURITY SYMPOSIUM, 2018, : 513 - 529
  • [9] FriendlyFoe: Adversarial Machine Learning as a Practical Architectural Defense against Side Channel Attacks
    Nam, Hyoungwook
    Pothukuchi, Raghavendra Pradyumna
    Li, Bo
    Kim, Nam Sung
    Torrellas, Josep
    PROCEEDINGS OF THE 2024 THE INTERNATIONAL CONFERENCE ON PARALLEL ARCHITECTURES AND COMPILATION TECHNIQUES, PACT 2024, 2024, : 338 - 350
  • [10] Adversarial Machine Learning Attacks against Intrusion Detection Systems: A Survey on Strategies and Defense
    Alotaibi, Afnan
    Rassam, Murad A.
    FUTURE INTERNET, 2023, 15 (02)