Xie Zhenpeng, Shen Gongzhang. Study on effectiveness evaluation of integrated control system with laser guided bomb[J]. Journal of Beijing University of Aeronautics and Astronautics, 2003, 29(12): 1123-1126. (in Chinese)
Citation: LIU Hongyi, FANG Yutong, WEN Weipinget al. A method for filtering the attack pairs of adversarial examples based on attack distance[J]. Journal of Beijing University of Aeronautics and Astronautics, 2022, 48(2): 339-347. doi: 10.13700/j.bh.1001-5965.2020.0529(in Chinese)

A method for filtering the attack pairs of adversarial examples based on attack distance

doi: 10.13700/j.bh.1001-5965.2020.0529
Funds:

National Natural Science Foundation of China U1736218

More Information
  • Corresponding author: WEN Weiping, E-mail: weipingwen@ss.pku.edu.cn
  • Received Date: 21 Sep 2020
  • Accepted Date: 06 Nov 2020
  • Publish Date: 20 Feb 2022
  • During the generation of black-box adversarial examples, an attack pair is usually specified, including a source example and a target example. The purpose is to let the generated adversarial example only have little norm difference from the source example, but it is recognized by the classifier as the classification of the target sample. In order to solve the problem of the instability of adversarial attacks caused by different attack difficulty of attack pairs, taking the image recognition field as an example, this paper presented an attack distance measurement method based on the length of the decision boundary, which provided a measurement method for the attack difficulty of attack pairs. Then this paper designed a filtering method based on attack distance of the attack pairs, which filtered out attack pairs that were difficult to attack before the attack started, so this method can improve the attack performance without modifying the attack algorithm. Experiments show that, compared with the attack pairs before filtering, the filtered attack pairs improve the overall attack performance by 42.07%, improve the attack efficiency by 24.99%, and stabilize the variance by 76.23%. It is recommended that all methods of generating adversarial examples using attack pairs should filter attack pairs before attack to stabilize and improve the attack performance.

     

  • [1]
    KRIZHEVSKY A, SUTSKEVER I, HINTON G E. ImageNet classification with deep convolutional neural networks[J]. Communications of the ACM, 2017, 60(6): 84-90. doi: 10.1145/3065386
    [2]
    SZEGEDY C, LIU W, JIA Y Q, et al. Going deeper with convolutions[C]//2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway: IEEE Press, 2015: 1-9.
    [3]
    SIMONYAN K, ZISSERMAN A. Very deep convolutional networks for large-scale image recognition[EB/OL]. (2015-04-10)[2020-09-21].
    [4]
    HE K M, ZHANG X Y, REN S Q, et al. Deep residual learning for image recognition[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway: IEEE Press, 2016: 770-778.
    [5]
    HUANG G, LIU Z, VAN DER MAATEN L, et al. Densely connected convolutional networks[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway: IEEE Press, 2017: 2261-2269.
    [6]
    SZEGEDY C, ZAREMBA W, SUTSKEVER I, et al. Intriguing properties of neural networks[EB/OL]. (2014-02-19)[2020-09-21].
    [7]
    GOODFELLOW I J, SHLENS J, SZEGEDY C. Explaining and harnessing adversarial examples[EB/OL]. (2015-05-20)[2020-09-21].
    [8]
    KURAKIN A, GOODFELLOW I, BENGIO S. Adversarial machine learning at scale[EB/OL]. (2017-02-11)[2020-09-21].
    [9]
    MADRY A, MAKELOV A, SCHMIDT L, et al. Towards deep learning models resistant to adversarial attacks[EB/OL]. (2019-09-04)[2020-09-21].
    [10]
    DONG Y P, LIAO F Z, PANG T, et al. Boosting adversarial attacks with momentum[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE Press, 2018: 9185-9193.
    [11]
    CARLINI N, WAGNER D. Towards evaluating the robustness of neural networks[C]//2017 IEEE Symposium on Security and Privacy (SP). Piscataway: IEEE Press, 2017: 39-57.
    [12]
    PAPERNOT N, MCDANIEL P, JHA S, et al. The limitations of deep learning in adversarial settings[C]//2016 IEEE European Symposium on Security and Privacy (EuroS&P). Piscataway: IEEE Press, 2016: 372-387.
    [13]
    MOOSAVI-DEZFOOLI S M, FAWZI A, FROSSARD P. DeepFool: A simple and accurate method to fool deep neural networks[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway: IEEE Press, 2016: 2574-2582.
    [14]
    PAPERNOT N, MCDANIEL P, GOODFELLOW I, et al. Practical black-box attacks against deep learning systems using adversarial examples[EB/OL]. (2017-05-19)[2020-09-21].
    [15]
    XIE C H, ZHANG Z S, ZHOU Y Y, et al. Improving transferability of adversarial examples with input diversity[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE Press, 2019: 2725-2734.
    [16]
    TRAMER F, KURAKIN A, PAPERNOT N, et al. Ensemble adversarial training: Attacks and defenses[EB/OL]. (2020-04-26)[2020-09-21].
    [17]
    ILYAS A, ENGSTROM L, ATHALYE A, et al. Black-box adversarial attacks with limited queries and information[C]//International Conference on Machine Learning, 2018: 2137-2146.
    [18]
    KUANG X H, LIU H Y, WANG Y, et al. A CMA-ES-based adversarial attack on black-box deep neural networks[J]. IEEE Access, 2019, 7: 172938-172947. doi: 10.1109/ACCESS.2019.2956553
    [19]
    DONG Y P, SU H, WU B Y, et al. Efficient decision-based black-box adversarial attacks on face recognition[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE Press, 2019: 7706-7714.
    [20]
    BRENDEL W, RAUBER J, BETHGE M. Decision-based adversarial attacks: Reliable attacks against black-box machine learning models[EB/OL]. (2018-02-16)[2020-09-21].
    [21]
    LECUN Y, BENGIO Y, HINTON G. Deep learning[J]. Nature, 2015, 521(7553): 436-444. doi: 10.1038/nature14539
    [22]
    HELMSTAEDTER M, BRIGGMAN K L, TURAGA S C, et al. Connectomic reconstruction of the inner plexiform layer in the mouse retina[J]. Nature, 2013, 500(7461): 168-174. doi: 10.1038/nature12346
    [23]
    XIONG H Y, ALIPANAHI B, LEE L J, et al. The human splicing code reveals new insights into the genetic determinants of disease[J]. Science, 2015, 347(6218): 1254806. doi: 10.1126/science.1254806
    [24]
    HINTON G, DENG L, YU D, et al. Deep neural networks for acoustic modeling in speech recognition: The shared views of four research groups[J]. IEEE Signal Processing Magazine, 2012, 29(6): 82-97. doi: 10.1109/MSP.2012.2205597
    [25]
    SUTSKEVER I, VINYALS O, LE Q V. Sequence to sequence learning with neural networks[C]//Annual Conference on Neural Information Processing Systems (NeurIPS). Cambridge: MIT Press, 2014: 3104-3112.
    [26]
    MNIH V, KAVUKCUOGLU K, SILVER D, et al. Human-level control through deep reinforcement learning[J]. Nature, 2015, 518(7540): 529-533. doi: 10.1038/nature14236
    [27]
    GIUSTI A, GUZZI J, CIRŞAN D C, et al. A machine learning approach to visual perception of forest trails for mobile robots[J]. IEEE Robotics and Automation Letters, 2016, 1(2): 661-667. doi: 10.1109/LRA.2015.2509024
    [28]
    MIDDLEHURST C. China unveils world's first facial recognition atm[EB/OL]. (2015-01-01)[2020-09-01].
    [29]
    刘恒, 吴德鑫, 徐剑. 基于生成式对抗网络的通用性对抗扰动生成方法[J]. 信息网络安全, 2020, 20(5): 57-64.

    LIU H, WU D X, XU J. Generating universal adversarial perturbations with generative adversarial networks[J]. Netinfo Security, 2020, 20(5): 57-64(in Chinese).
    [30]
    HUANG Q, KATSMAN I, GU Z Q, et al. Enhancing adversarial example transferability with an intermediate level attack[C]//2019 IEEE/CVF International Conference on Computer Vision. Piscataway: IEEE Press, 2019: 4732-4741.
    [31]
    WIERSTRA D, SCHAUL T, PETERS J, et al. Natural evolution strategies[C]//2008 IEEE Congress on Evolutionary Computation (IEEE World Congress on Computational Intelligence). Piscataway: IEEE Press, 2008: 3381-3387.
    [32]
    HANSEN N. The CMA evolution strategy: A tutorial[EB/OL]. (2016-04-04)[2020-09-21].
    [33]
    侯留洋, 罗森林, 潘丽敏, 等. 融合多特征的Android恶意软件检测方法[J]. 信息网络安全, 2020, 20(1): 67-74.

    HOU L Y, LUO S L, PAN L M, et al. Multi-feature Android malware detection method[J]. Netinfo Security, 2020, 20(1): 67-74(in Chinese).
  • Relative Articles

    [1]DAI Xuan, MA Yunxiang, LI Chao, WANG Genye, DAI Huisheng, LIU Lei. Anti-erosionperformance tests of cement stabilized macadam base considering apparent erosion and image evolution[J]. Journal of Beijing University of Aeronautics and Astronautics. doi: 10.13700/j.bh.1001-5965.2024.0844
    [2]LYU Y L,GOU Y,LI M,et al. Ship detection method based on attentional guidance and multi-sample decision[J]. Journal of Beijing University of Aeronautics and Astronautics,2025,51(1):202-213 (in Chinese). doi: 10.13700/j.bh.1001-5965.2022.1004.
    [3]WANG Shiqi, LU Hui, ZHANG Yuxuan. Hexagonal grid sampling method for low-dimensional decision boundary identification[J]. Journal of Beijing University of Aeronautics and Astronautics. doi: 10.13700/j.bh.1001-5965.2024.0526
    [4]GUAN Y Z,FENG M. Application of active disturbance rejection control in gyro motor steady speed control[J]. Journal of Beijing University of Aeronautics and Astronautics,2024,50(1):234-242 (in Chinese). doi: 10.13700/j.bh.1001-5965.2022.0209.
    [5]Cao Yueyao, Xue Tao, He Shanshan, Ai Jianliang, Dong Yiqun. Calculation of Beyond Visual Range Air Combat All-Domain Fire Field and Application of Situation Threat Assessment and Assisted Decision Making[J]. Journal of Beijing University of Aeronautics and Astronautics. doi: 10.13700/j.bh.1001-5965.2024.0399
    [6]XING Xue, WANG Shunan, DING Jianjun, MA Bingjie, WANG Shuai, DU Jingtao. Thermoacoustic coupling characteristics prediction and experimental study of Rijke tube with impedance boundaries[J]. Journal of Beijing University of Aeronautics and Astronautics. doi: 10.13700/j.bh.1001-5965.2024.0644
    [7]WU Z Y,GAO Z X,CHEN X M,et al. Mach number effect in shock-wave/turbulent-boundary-layer interaction flow[J]. Journal of Beijing University of Aeronautics and Astronautics,2024,50(11):3484-3494 (in Chinese). doi: 10.13700/j.bh.1001-5965.2022.0857.
    [8]YANG Rong-tai, SHAO Yu-bin, DU Qing-zhi, LONG Hua, QI Yu-ting, ZHANG Feng. Few-shot entity linking prediction based on Graph-Transformer network[J]. Journal of Beijing University of Aeronautics and Astronautics. doi: 10.13700/j.bh.1001-5965.2024.0023
    [9]CHANG Jiaming, LI Sulan, DUAN Xuechao, ZHANG Wei, WANG Chenyang. Anti-stochastic disturbance control of airship[J]. Journal of Beijing University of Aeronautics and Astronautics. doi: 10.13700/j.bh.1001-5965.2024.0489
    [10]LI H G,WANG Y F,YANG L C. Meta-learning-based few-shot object detection for remote sensing images[J]. Journal of Beijing University of Aeronautics and Astronautics,2024,50(8):2503-2513 (in Chinese). doi: 10.13700/j.bh.1001-5965.2022.0637.
    [11]ZHANG Fan, LIU Wan, GUO Yong-yan, CENG Zhi-chun, HE Qian-wei, ZHAO Zhong. The application and practice of black box testing technology in Fluid Simulation Software[J]. Journal of Beijing University of Aeronautics and Astronautics. doi: 10.13700/j.bh.1001-5965.2023.0621
    [12]LI M H,JIN S,DU Y. Adversarial attack method based on loss smoothing[J]. Journal of Beijing University of Aeronautics and Astronautics,2024,50(2):663-670 (in Chinese). doi: 10.13700/j.bh.1001-5965.2022.0478.
    [13]SHI Z,WANG B,YANG B,et al. Single-event radiation hardening method for 14 nm pFinFET device[J]. Journal of Beijing University of Aeronautics and Astronautics,2023,49(12):3335-3342 (in Chinese). doi: 10.13700/j.bh.1001-5965.2022.0071.
    [14]WANG Z Q,LI J,LI J,et al. UAV swarm decision methods under weak information interaction conditions[J]. Journal of Beijing University of Aeronautics and Astronautics,2023,49(12):3489-3499 (in Chinese). doi: 10.13700/j.bh.1001-5965.2022.0066.
    [15]PENG Yu-xiao, HE Zhen, CHOU Jing-wen. Active Deformation Decision-Making for a Four-wing Variable Sweep Aircraft based on LSTM-DDPG Algorithm[J]. Journal of Beijing University of Aeronautics and Astronautics. doi: 10.13700/j.bh.1001-5965.2023.0513
    [16]ZHANG Yun-jie, ZHOU Jie-xin, ZHANG Feng-zhe, ZHOU Rui, ZOU Ting. Reachability Evaluation Method for Ballistic Missile Based on Extended Boundary Method[J]. Journal of Beijing University of Aeronautics and Astronautics. doi: 10.13700/j.bh.1001-5965.2023.0630
    [17]SUN Xiao-kun, CHEN Yang, HU Can-bin, XIANG De-liang. SAR target recognition method under limited measured sample conditions[J]. Journal of Beijing University of Aeronautics and Astronautics. doi: 10.13700/j.bh.1001-5965.2023.0648
    [18]ZHANG Zhi, YI Hua-hui, ZHENG Jin. Few-Shot Object Detection of Aerial Image Based on Language Guidance Vision[J]. Journal of Beijing University of Aeronautics and Astronautics. doi: 10.13700/j.bh.1001-5965.2023.0491
    [19]HU Kai, ZHAO Jian, LIU Yu, NIU Yukai, JI Gang. Images inpainting via structure guidance[J]. Journal of Beijing University of Aeronautics and Astronautics, 2022, 48(7): 1269-1277. doi: 10.13700/j.bh.1001-5965.2021.0004
    [20]ZHANG Xuejun, BAO Junda, HE Fucun, GAI Jiyang, TIAN Feng, HUANG Haiyan. A fingerprint indoor localization method against adversarial sample attacks[J]. Journal of Beijing University of Aeronautics and Astronautics, 2022, 48(11): 2087-2101. doi: 10.13700/j.bh.1001-5965.2021.0789
  • 加载中

Catalog

    通讯作者: 陈斌, bchen63@163.com
    • 1. 

      沈阳化工大学材料科学与工程学院 沈阳 110142

    1. 本站搜索
    2. 百度学术搜索
    3. 万方数据库搜索
    4. CNKI搜索

    Figures(6)  / Tables(1)

    Article Metrics

    Article views(421) PDF downloads(96) Cited by()
    Proportional views
    Related

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return