Forming Adversarial Example Attacks Against Deep Neural Networks With Reinforcement Learning

被引：0
|
作者：
Akers, Matthew [1 ]
Barton, Armon [2 ]
机构：
[1] US Second Fleet, Hampton Rd, Norfolk, VA 23455 USA
[2] Dept Comp Sci Naval Postgrad Sch, Dept Comp Sci, Monterey, CA 93943 USA
来源：
COMPUTER | 2024年 / 57卷 / 01期
关键词：
Deep learning; Perturbation methods; Reinforcement learning; Artificial neural networks; GAME; GO;
D O I：
10.1109/MC.2023.3324751
中图分类号：
TP3 [计算技术、计算机技术];
学科分类号：
0812 ;
摘要：
We propose a novel reinforcement learning-based adversarial example attack, Adversarial Reinforcement Learning Agent, designed to learn imperceptible perturbation that causes misclassification when added to the input of a deep learning classifier.
引用
收藏
页码：88 / 99
页数：12
相关论文
共 50 条
  • [31] Analyzing Adversarial Attacks Against Deep Learning for Intrusion Detection in IoT Networks
    Ibitoye, Olakunle
    Shafiq, Omair
    Matrawy, Ashraf
    2019 IEEE GLOBAL COMMUNICATIONS CONFERENCE (GLOBECOM), 2019,
  • [32] Fortifying graph neural networks against adversarial attacks via ensemble learning
    Zhou, Chenyu
    Huang, Wei
    Miao, Xinyuan
    Peng, Yabin
    Kong, Xianglong
    Cao, Yi
    Chen, Xi
    KNOWLEDGE-BASED SYSTEMS, 2025, 309
  • [33] SIT: Stochastic Input Transformation to Defend Against Adversarial Attacks on Deep Neural Networks
    Guesmi, Amira
    Alouani, Ihsen
    Baklouti, Mouna
    Frikha, Tarek
    Abid, Mohamed
    IEEE DESIGN & TEST, 2022, 39 (03) : 63 - 72
  • [34] Adversarial Attacks in a Deep Reinforcement Learning based Cluster Scheduler
    Zhang, Shaojun
    Wang, Chen
    Zomaya, Albert Y.
    2020 IEEE 28TH INTERNATIONAL SYMPOSIUM ON MODELING, ANALYSIS, AND SIMULATION OF COMPUTER AND TELECOMMUNICATION SYSTEMS (MASCOTS 2020), 2020, : 1 - 8
  • [35] Critical State Detection for Adversarial Attacks in Deep Reinforcement Learning
    Kumar, Praveen R.
    Kumar, Niranjan, I
    Sivasankaran, Sujith
    Vamsi, Mohan A.
    Vijayaraghavan, Vineeth
    20TH IEEE INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND APPLICATIONS (ICMLA 2021), 2021, : 1761 - 1766
  • [36] Robust Deep Reinforcement Learning with Adversarial Attacks Extended Abstract
    Pattanaik, Anay
    Tang, Zhenyi
    Liu, Shuijing
    Bommannan, Gautham
    Chowdhary, Girish
    PROCEEDINGS OF THE 17TH INTERNATIONAL CONFERENCE ON AUTONOMOUS AGENTS AND MULTIAGENT SYSTEMS (AAMAS' 18), 2018, : 2040 - 2042
  • [37] A Survey on Attacks and Their Countermeasures in Deep Learning: Applications in Deep Neural Networks, Federated, Transfer, and Deep Reinforcement Learning
    Ali, Haider
    Chen, Dian
    Harrington, Matthew
    Salazar, Nathaniel
    Al Ameedi, Mohannad
    Khan, Ahmad Faraz
    Butt, Ali R.
    Cho, Jin-Hee
    IEEE ACCESS, 2023, 11 : 120095 - 120130
  • [38] Real-Time Adversarial Perturbations Against Deep Reinforcement Learning Policies: Attacks and Defenses
    Tekgul, Buse G. A.
    Wang, Shelly
    Marchal, Samuel
    Asokan, N.
    COMPUTER SECURITY - ESORICS 2022, PT III, 2022, 13556 : 384 - 404
  • [39] Deep Learning Defense Method Against Adversarial Attacks
    Wang, Ling
    Zhang, Cheng
    Liu, Jie
    2020 IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN, AND CYBERNETICS (SMC), 2020, : 3667 - 3671
  • [40] Defending Deep Learning Models Against Adversarial Attacks
    Mani, Nag
    Moh, Melody
    Moh, Teng-Sheng
    INTERNATIONAL JOURNAL OF SOFTWARE SCIENCE AND COMPUTATIONAL INTELLIGENCE-IJSSCI, 2021, 13 (01): : 72 - 89
12345