Changes between Version 20 and Version 21 of Other/Summer/2020/AdvML


Ignore:
Timestamp:
Jul 6, 2020, 4:17:36 AM (6 months ago)
Author:
yb220
Comment:

Legend:

Unmodified
Added
Removed
Modified
  • Other/Summer/2020/AdvML

    v20 v21  
    2828- Statistical Pooling: https://www.tensorflow.org/api_docs/python/tf/nn/moments
    2929- Probabilistic Linear Discriminant Analysis for Inferences About Identity: https://www.orbit-lab.org/attachment/wiki/Other/Summer/2020/AdvML/Probabilistic%20Linear%20Discriminant%20Analysis%20for%20Inferences%20About%20Identity.pdf
     30*Week 6
     31- Introduction of Fast Gradient Sign Method (FSGM): https://towardsdatascience.com/perhaps-the-simplest-introduction-of-adversarial-examples-ever-c0839a759b8d#:~:text=Fast%20Gradient%20Sign%20Method%20(FGSM)&text=In%20essence%2C%20FGSM%20is%20to,small%20number%20via%20max%20norm.
     32- Adversarial example using FGSM: https://www.tensorflow.org/tutorials/generative/adversarial_fgsm
     33- Cross-entropy cost function: https://eng.libretexts.org/Bookshelves/Computer_Science/Book%3A_Neural_Networks_and_Deep_Learning_(Nielsen)/03%3A_Improving_the_way_neural_networks_learn/3.01%3A_The_cross-entropy_cost_function
    3034
    3135== Reading Material ==
     
    7377- Read the paper: Practical Adversarial Attacks Against Speaker Recognition Systems (HotMobile’20) and get familiar with the untargeted attack
    7478
     79== Week 6 Activities ==
     80- Develop an untargeted attack that can generate adversarial samples based on the sample code and tutorial. \\
     81   -- Understand Fast Gradient Sign Method (FSGM) \\
     82   -- Understand cross-entropy as cost function \\
     83- Evaluate the performance of the adversarial samples on the voice assistant system (X-Vector).
     84
    7585== Project Website ==
    7686- [https://chunnubansal.wixsite.com/winlab-amlavas]