8000 sebszyller (Sebastian Szyller) · GitHub
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content
View sebszyller's full-sized avatar
🗯️
Exception occurred while trying to handle a previously thrown exception.
🗯️
Exception occurred while trying to handle a previously thrown exception.
12 followers · 0 following

Achievements

Achievement: Pull SharkAchievement: StarstruckAchievement: Arctic Code Vault Contributor

Achievements

Achievement: Pull SharkAchievement: StarstruckAchievement: Arctic Code Vault Contributor

Block or report sebszyller

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
sebszyller/README.md

Profile pic generated with DALL-E 2 using the prompt:

a realistic oil painting of a tabby cat in a pirate outfit, ocean background

Hello there

My name is Sebastian and I'm a research scientist at Intel Labs. I work on security and privacy of machine learning.

You can get a better idea by looking at my publication list (Google Scholar) or blog posts.

Recently, our team released LLMart -- a state-of-the-art library for optimising adversarial prompts.

Here you can find the forks of the official releases of my scientific work:

as well as some tinkering projects:

(I use neovim, btw)

Pinned Loading

  1. ssg-research/dawn-dynamic-adversarial-watermarking-of-neural-networks ssg-research/dawn-dynamic-adversarial-watermarking-of-neural-networks Public

    Watermarking against model extraction attacks in MLaaS. ACM MM 2021.

    Jupyter Notebook 33 5

  2. SSGAalto/prada-protecting-against-dnn-model-stealing-attacks SSGAalto/prada-protecting-against-dnn-model-stealing-attacks Public

    Reference implementation of the PRADA model stealing defense. IEEE Euro S&P 2019.

    Python 33 11

  3. IntelLabs/LLMart IntelLabs/LLMart Public

    LLM Adversarial Robustness Toolkit, a toolkit for evaluating LLM robustness through adversarial testing.

    Python 35 5

  4. rust-with-llms rust-with-llms Public

    Learning rust with the help of ChatGPT

    Rust 2

0