blog.trailofbits.com/2021/03/15/never-a-dill-moment-exploiting-machine-learning-pickle-files

Preview meta tags from the blog.trailofbits.com website.

Linked Hostnames

16

Thumbnail

Search Engine Appearance

Google

https://blog.trailofbits.com/2021/03/15/never-a-dill-moment-exploiting-machine-learning-pickle-files

Never a dill moment: Exploiting machine learning pickle files

Many machine learning (ML) models are Python pickle files under the hood, and it makes sense. The use of pickling conserves memory, enables start-and-stop model training, and makes trained models portable (and, thereby, shareable). Pickling is easy to implement, is built into Python without requiring additional dependencies, and supports serialization of custom […]



Bing

Never a dill moment: Exploiting machine learning pickle files

https://blog.trailofbits.com/2021/03/15/never-a-dill-moment-exploiting-machine-learning-pickle-files

Many machine learning (ML) models are Python pickle files under the hood, and it makes sense. The use of pickling conserves memory, enables start-and-stop model training, and makes trained models portable (and, thereby, shareable). Pickling is easy to implement, is built into Python without requiring additional dependencies, and supports serialization of custom […]



DuckDuckGo

https://blog.trailofbits.com/2021/03/15/never-a-dill-moment-exploiting-machine-learning-pickle-files

Never a dill moment: Exploiting machine learning pickle files

Many machine learning (ML) models are Python pickle files under the hood, and it makes sense. The use of pickling conserves memory, enables start-and-stop model training, and makes trained models portable (and, thereby, shareable). Pickling is easy to implement, is built into Python without requiring additional dependencies, and supports serialization of custom […]

  • General Meta Tags

    7
    • title
      Never a dill moment: Exploiting machine learning pickle files -The Trail of Bits Blog
    • charset
      UTF-8
    • viewport
      width=device-width,initial-scale=1
    • description
      Many machine learning (ML) models are Python pickle files under the hood, and it makes sense. The use of pickling conserves memory, enables start-and-stop model training, and makes trained models portable (and, thereby, shareable). Pickling is easy to implement, is built into Python without requiring additional dependencies, and supports serialization of custom […]
    • article:section
      posts

  • Open Graph Meta Tags

    7
    • og:url
      https://blog.trailofbits.com/2021/03/15/never-a-dill-moment-exploiting-machine-learning-pickle-files/
    • og:site_name
      The Trail of Bits Blog
    • og:title
      Never a dill moment: Exploiting machine learning pickle files
    • og:description
      Many machine learning (ML) models are Python pickle files under the hood, and it makes sense. The use of pickling conserves memory, enables start-and-stop model training, and makes trained models portable (and, thereby, shareable). Pickling is easy to implement, is built into Python without requiring additional dependencies, and supports serialization of custom […]
    • US country flagog:locale
      en_us

  • Twitter Meta Tags

    4
    • twitter:card
      summary_large_image
    • twitter:image
      https://blog.trailofbits.com/img/Trail-of-Bits-Open-Graph.png
    • twitter:title
      Never a dill moment: Exploiting machine learning pickle files
    • twitter:description
      Many machine learning (ML) models are Python pickle files under the hood, and it makes sense. The use of pickling conserves memory, enables start-and-stop model training, and makes trained models portable (and, thereby, shareable). Pickling is easy to implement, is built into Python without requiring additional dependencies, and supports serialization of custom […]

  • Item Prop Meta Tags

    7
    • name
      Never a dill moment: Exploiting machine learning pickle files
    • description
      Many machine learning (ML) models are Python pickle files under the hood, and it makes sense. The use of pickling conserves memory, enables start-and-stop model training, and makes trained models portable (and, thereby, shareable). Pickling is easy to implement, is built into Python without requiring additional dependencies, and supports serialization of custom […]
    • datePublished
      2021-03-15T11:06:18-04:00
    • dateModified
      2021-03-15T11:06:18-04:00
    • wordCount
      1893

  • Link Tags

    11
    • dns-prefetch
      //fonts.googleapis.com
    • dns-prefetch
      //fonts.gstatic.com
    • preconnect
      https://fonts.gstatic.com
    • shortcut icon
      /favicon.png
    • stylesheet
      https://fonts.googleapis.com/css2?family=Open+Sans:ital,wght@0,300..800;1,300..800&family=Rubik:ital,wght@0,300..900;1,300..900&display=swap

Links

29