1. 2022

    1. When reality is your adversary: failure modes of image recognition Saturday, Sep 17
    2. Is it illegal to hack a machine learning model? Sunday, Aug 28
    3. We're not so different, you and I -- adversarial attacks are poisonous Saturday, Aug 13
    4. How to tell if someone trained a model on your data Thursday, Jul 7
    5. Smiling is all you need: fooling identity recognition by having emotions Thursday, May 19
    6. Wear your sunglasses at night : fooling identity recognition with physical accessories Tuesday, Apr 12
    7. A faster way to generate backdoor attacks Thursday, Mar 31
    8. Poisoning deep learning algorithms Monday, Feb 28
    9. MLOps lessons from Creativity, Inc. (Part 2) Wednesday, Jan 26
    10. MLOps lessons from Creativity, Inc. (Part 1) Monday, Jan 17

  2. 2021

    1. Evading real-time detection with an adversarial t-shirt Monday, Nov 29
    2. Evading CCTV cameras with adversarial patches Wednesday, Nov 10
    3. There's treasure everywhere: a devops perspective on the Port of Long Beach Tuesday, Nov 2
    4. Fooling AI in real life with adversarial patches Wednesday, Oct 20
    5. What is adversarial machine learning? Saturday, Sep 25
    6. Fast operations on scikit-learn decision trees with numba Tuesday, Sep 7
    7. SciPy Proceedings 2021 Survey Sunday, Aug 15
    8. Writing an image annotation tool in 50 lines of Python Wednesday, Jul 28
    9. SciPy is partnering with JOSS! Part 1 Monday, Jun 14
    10. How to add plots to docstrings Wednesday, Apr 28
    11. Getting started with timeseries data augmentation Wednesday, Mar 24
    12. Virtual epochs for PyTorch Monday, Feb 15
    13. Superconvergence in PyTorch Wednesday, Jan 20

  3. 2020

    1. A faster way to generate thin plate splines Saturday, Dec 19
    2. How to combine variable length sequences in PyTorch DataLoaders Saturday, Sep 26
    3. Adding data augmentation to torchtext datasets Sunday, Aug 30
    4. SciPy Proceedings 2020 Survey Thursday, Jul 23
    5. Installing cuda on Ubuntu 18.04 for pytorch or tensorflow Sunday, Apr 19
    6. Three reasons to use Shapley values Thursday, Mar 26
    7. How Shapley values work Saturday, Feb 29
    8. A multi-file torchtext data loader Thursday, Jan 30

  4. 2019

    1. A faster way to generate lagged values Saturday, Dec 28