Background Class Defense Against Adversarial Examples

被引：7
|
作者：
McCoyd, Michael [1 ]
Wagner, David [1 ]
机构：
[1] Univ Calif Berkeley, Berkeley, CA 94720 USA
来源：
2018 IEEE SYMPOSIUM ON SECURITY AND PRIVACY WORKSHOPS (SPW 2018) | 2018年
关键词：
D O I：
10.1109/SPW.2018.00023
中图分类号：
TP [自动化技术、计算机技术];
学科分类号：
0812 ;
摘要：
Adversarial examples allow crafted attacks against deep neural network classification of images. We propose a defense of expanding the training set with a single, large, and diverse class of background images, striving to 'fill' around the borders of the classification boundary. We find it aids detection of simple attacks on EMNIST, but not advanced attacks. We discuss several limitations of our examination.
引用
收藏
页码：96 / 102
页数：7
相关论文
共 50 条
  • [21] DeepMTD: Moving Target Defense for Deep Visual Sensing against Adversarial Examples
    Song, Qun
    Yan, Zhenyu
    Tan, Rui
    ACM TRANSACTIONS ON SENSOR NETWORKS, 2022, 18 (01)
  • [22] Moving Target Defense for Embedded Deep Visual Sensing against Adversarial Examples
    Song, Qun
    Yan, Zhenyu
    Tan, Rui
    PROCEEDINGS OF THE 17TH CONFERENCE ON EMBEDDED NETWORKED SENSOR SYSTEMS (SENSYS '19), 2019, : 124 - 137
  • [23] Detection Based Defense Against Adversarial Examples From the Steganalysis Point of View
    Liu, Jiayang
    Zhang, Weiming
    Zhang, Yiwei
    Hou, Dongdong
    Liu, Yujia
    Zha, Hongyue
    Yu, Nenghai
    2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019), 2019, : 4820 - 4829
  • [24] Complete Defense Framework to Protect Deep Neural Networks against Adversarial Examples
    Sun, Guangling
    Su, Yuying
    Qin, Chuan
    Xu, Wenbo
    Lu, Xiaofeng
    Ceglowski, Andrzej
    MATHEMATICAL PROBLEMS IN ENGINEERING, 2020, 2020
  • [25] On the Limitation of MagNet Defense against L1-based Adversarial Examples
    Lu, Pei-Hsuan
    Chen, Pin-Yu
    Chen, Kang-Cheng
    Yu, Chia-Mu
    2018 48TH ANNUAL IEEE/IFIP INTERNATIONAL CONFERENCE ON DEPENDABLE SYSTEMS AND NETWORKS WORKSHOPS (DSN-W), 2018, : 200 - 214
  • [26] DeepMTD: Moving Target Defense for Deep Visual Sensing against Adversarial Examples
    Song, Qun
    Yan, Zhenyu
    Tan, Rui
    ACM Transactions on Sensor Networks, 2021, 18 (01)
  • [27] Markov Chain Based Efficient Defense Against Adversarial Examples in Computer Vision
    Zhou, Yue
    Hu, Xiaofang
    Wang, Lidan
    Duan, Shukai
    Chen, Yiran
    IEEE ACCESS, 2019, 7 : 5695 - 5706
  • [28] A robust defense for spiking neural networks against adversarial examples via input filtering
    Guo, Shasha
    Wang, Lei
    Yang, Zhijie
    Lu, Yuliang
    JOURNAL OF SYSTEMS ARCHITECTURE, 2024, 153
  • [29] Learning defense transformations for counterattacking adversarial examples
    Li, Jincheng
    Zhang, Shuhai
    Cao, Jiezhang
    Tan, Mingkui
    NEURAL NETWORKS, 2023, 164 : 177 - 185
  • [30] Adversarial Training Defense Based on Second-order Adversarial Examples
    Qian Yaguan
    Zhang Ximin
    Wang Bin
    Gu Zhaoquan
    Li Wei
    Yun Bensheng
    JOURNAL OF ELECTRONICS & INFORMATION TECHNOLOGY, 2021, 43 (11) : 3367 - 3373
12345