On the Relationship between Generalization and Robustness to Adversarial Examples

被引:8
|
作者
Pedraza, Anibal [1 ]
Deniz, Oscar [1 ]
Bueno, Gloria [1 ]
机构
[1] Univ Castilla La Mancha, VISILAB, ETSII, Ciudad Real 13071, Spain
来源
SYMMETRY-BASEL | 2021年 / 13卷 / 05期
关键词
machine learning; computer vision; deep learning; adversarial examples; adversarial robustness; overfitting;
D O I
10.3390/sym13050817
中图分类号
O [数理科学和化学]; P [天文学、地球科学]; Q [生物科学]; N [自然科学总论];
学科分类号
07 ; 0710 ; 09 ;
摘要
One of the most intriguing phenomenons related to deep learning is the so-called adversarial examples. These samples are visually equivalent to normal inputs, undetectable for humans, yet they cause the networks to output wrong results. The phenomenon can be framed as a symmetry/asymmetry problem, whereby inputs to a neural network with a similar/symmetric appearance to regular images, produce an opposite/asymmetric output. Some researchers are focused on developing methods for generating adversarial examples, while others propose defense methods. In parallel, there is a growing interest in characterizing the phenomenon, which is also the focus of this paper. From some well known datasets of common images, like CIFAR-10 and STL-10, a neural network architecture is first trained in a normal regime, where training and validation performances increase, reaching generalization. Additionally, the same architectures and datasets are trained in an overfitting regime, where there is a growing disparity in training and validation performances. The behaviour of these two regimes against adversarial examples is then compared. From the results, we observe greater robustness to adversarial examples in the overfitting regime. We explain this simultaneous loss of generalization and gain in robustness to adversarial examples as another manifestation of the well-known fitting-generalization trade-off.
引用
收藏
页数:13
相关论文
共 50 条
  • [31] Deep Fusion: Crafting Transferable Adversarial Examples and Improving Robustness of Industrial Artificial Intelligence of Things
    Wang, Yajie
    Tan, Yu-an
    Baker, Thar
    Kumar, Neeraj
    Zhang, Quanxin
    IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS, 2023, 19 (06) : 7480 - 7488
  • [32] An Empirical Study on the Relation Between Network Interpretability and Adversarial Robustness
    Noack A.
    Ahern I.
    Dou D.
    Li B.
    SN Computer Science, 2021, 2 (1)
  • [33] On the Salience of Adversarial Examples
    Fernandez, Amanda
    ADVANCES IN VISUAL COMPUTING, ISVC 2019, PT II, 2019, 11845 : 221 - 232
  • [34] Evaluating Adversarial Robustness with Expected Viable Performance
    McCoppin, Ryan
    Dawson, Colin
    Kennedy, Scan
    Blaha, Leslie M.
    22ND IEEE INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND APPLICATIONS, ICMLA 2023, 2023, : 76 - 82
  • [35] Generation and Countermeasures of adversarial examples on vision: a survey
    Liu, Jiangfan
    Li, Yishan
    Guo, Yanming
    Liu, Yu
    Tang, Jun
    Nie, Ying
    ARTIFICIAL INTELLIGENCE REVIEW, 2024, 57 (08)
  • [36] Evaluating and Enhancing the Robustness of Retrieval-Based Dialogue Systems with Adversarial Examples
    Li, Jia
    Tao, Chongyang
    Peng, Nanyun
    Wu, Wei
    Zhao, Dongyan
    Yan, Rui
    NATURAL LANGUAGE PROCESSING AND CHINESE COMPUTING (NLPCC 2019), PT I, 2019, 11838 : 142 - 154
  • [37] Survey on Generating Adversarial Examples
    Pan W.-W.
    Wang X.-Y.
    Song M.-L.
    Chen C.
    Ruan Jian Xue Bao/Journal of Software, 2020, 31 (01): : 67 - 81
  • [38] Adversarial Examples in Remote Sensing
    Czaja, Wojciech
    Fendley, Neil
    Pekala, Michael
    Ratto, Christopher
    Wang, I-Jeng
    26TH ACM SIGSPATIAL INTERNATIONAL CONFERENCE ON ADVANCES IN GEOGRAPHIC INFORMATION SYSTEMS (ACM SIGSPATIAL GIS 2018), 2018, : 408 - 411
  • [39] Detecting chaos in adversarial examples
    Deniz, Oscar
    Pedraza, Anibal
    Bueno, Gloria
    CHAOS SOLITONS & FRACTALS, 2022, 163
  • [40] Really natural adversarial examples
    Anibal Pedraza
    Oscar Deniz
    Gloria Bueno
    International Journal of Machine Learning and Cybernetics, 2022, 13 : 1065 - 1077