Noise is Inside Me! Generating Adversarial Perturbations with Noise Derived from Natural Filters

被引:14
作者
Agarwal, Akshay [1 ]
Vatsa, Mayank [2 ]
Singh, Richa [2 ]
Ratha, Nalini K. [3 ]
机构
[1] IIIT Delhi, Delhi, India
[2] IIT Jodhpur, Jodhpur, Rajasthan, India
[3] IBM TJ Watson Res Ctr, Seattle, WA USA
来源
2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS (CVPRW 2020) | 2020年
关键词
IMAGE QUALITY ASSESSMENT; IDENTIFICATION; WATERMARKING;
D O I
10.1109/CVPRW50498.2020.00395
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Deep learning solutions are vulnerable to adversarial perturbations and can lead a "frog" image to be misclassified as a "deer" or random pattern into "guitar". Adversarial attack generation algorithms generally utilize the knowledge of database and CNN model to craft the noise. In this research, we present a novel scheme termed as Camera Inspired Perturbations to generate adversarial noise. The proposed approach relies on the noise embedded in the image due to environmental factors or camera noise incorporated. We extract these noise patterns using image filtering algorithms and incorporate them into images to generate adversarial images. Unlike most of the existing algorithms that require learning of noise, the proposed adversarial noise can be applied in real-time. It is model-agnostic and can be utilized to fool multiple deep learning classifiers on various databases. The effectiveness of the proposed approach is evaluated on five different databases with five different convolutional neural networks such as ResNet-50, VGG-16, and VGG-Face. The proposed attack reduces the classification accuracy of every network, for instance, the performance of VGG-16 on the Tiny ImageNet database is reduced by more than 33%. The robustness of the proposed adversarial noise is also evaluated against different adversarial defense algorithms.
引用
收藏
页码:3354 / 3363
页数:10
相关论文
共 55 条
  • [11] Chhabra S, 2018, PROCEEDINGS OF THE TWENTY-SEVENTH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, P656
  • [12] Demontis A, 2019, PROCEEDINGS OF THE 28TH USENIX SECURITY SYMPOSIUM, P321
  • [13] Galloway A., 2019, ARXIV180403308
  • [14] Texture and art with deep neural networks
    Gatys, Leon A.
    Ecker, Alexander S.
    Bethge, Matthias
    [J]. CURRENT OPINION IN NEUROBIOLOGY, 2017, 46 : 178 - 186
  • [15] Geirhos R., 2019, P INT C LEARN REPR
  • [16] DeepRing: Protecting Deep Neural Network with Blockchain
    Goel, Akhil
    Agarwal, Akshay
    Vatsa, Mayank
    Singh, Richa
    Ratha, Nalini
    [J]. 2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS (CVPRW 2019), 2019, : 2821 - 2828
  • [17] Differential item functioning in the cognitive screener used in the Longitudinal Aging Study in India
    Goel, Ashish
    Gross, Alden
    [J]. INTERNATIONAL PSYCHOGERIATRICS, 2019, 31 (09) : 1331 - 1341
  • [18] Goodfellow Ian J., 2015, 3 INT C LEARN REPR I
  • [19] Detecting and Mitigating Adversarial Perturbations for Robust Face Recognition
    Goswami, Gaurav
    Agarwal, Akshay
    Ratha, Nalini
    Sing, Richa
    Vatsa, Mayank
    [J]. INTERNATIONAL JOURNAL OF COMPUTER VISION, 2019, 127 (6-7) : 719 - 742
  • [20] Goswami G, 2018, AAAI CONF ARTIF INTE, P6829