Sahbi Chaieb @sahbichaieb

Data Scientist / AI Engineer ∙ Tech enthusiast sahbichaieb.com Paris, France Joined June 2009

Tweets

345
Followers

269
Following

981
Likes

423

Google DeepMind @GoogleDeepMind

a month ago

What if you could not only watch a generated video, but explore it too? 🌐 Genie 3 is our groundbreaking world model that creates interactive, playable environments from a single text prompt. From photorealistic landscapes to fantasy realms, the possibilities are endless. 🧵

846 3K 14K 3.6M 4K

Download Video

Sahbi Chaieb @sahbichaieb

5 months ago

🏉💡 What if your rugby strategy was powered by AI ? In my latest piece, I apply @karpathy's idea of a council of LLMs to generate battlecards to win the next game. 🧠⚡ Read here: sahbichaieb.com/rugby-llm-coun… #RugbyAnalysis #AI #SportsTech

0 0 1 38 0

Sahbi Chaieb @sahbichaieb

a year ago

🏅 The Olympics may be over, but you can still score gold in AI security! 🔒 Check out the third article in my series on AI security. This one focuses on current tools to prevent prompt injection attacks in LLM systems: sahbichaieb.com/ai-security-to… #AI #Security #PromptInjection

0 2 1 68 0

SAS France @SASFrance

2 years ago

Notre 2ème #worshop "#IA et #DATA dans le #rugby international : la stratégie du XV de France" animé par @sahbichaieb 🤩 #BDAIP23 #IA #DATA @bigdataparis

0 2 3 285 0

Download Image

Sahbi Chaieb @sahbichaieb

2 years ago

Excited to share my new tool!🔒Analyze your profile & personality as seen by #ChatGPT. 🔥The goal is to raise awareness about #DataPrivacy . You can extract: -Personal Information -Life Summary -Personality Assessment -Hobbies/Interests github.com/sahbic/profile… #ResponsibleAI

1 1 11 489 4

TuringPost @TheTuringPost

3 years ago

5 open-source frameworks to ensure privacy in your ML: 1. @openminedorg PySyft 2. @TensorFlow Privacy 3. @IBM adversarial robustness toolbox 4. @metaai CrypTen 5. @MSFTResearch SEAL

0 17 69 0 21

Download Image

Sahbi Chaieb @sahbichaieb

4 years ago

Very interesting point of view on the future of Cloud services by @bernhardsson

Erik Bernhardsson @bernhardsson

4 years ago

Very interesting point of view on the future of Cloud services by @bernhardsson

55 80 496 0 167

0 0 1 0 0

Ulrich Paquet @ulrichpaquet

4 years ago

AI and ML students across Africa, this one is for you 🌍. Do you want to take your research to the next level 🚀? Applications are now open for DeepMind Scholarships at Stellenbosch University (MSc and PhD) 🎓! mlai.sun.ac.za/dms @StellenboschUni @DeepMind

9 122 208 0 34

Sahbi Chaieb @sahbichaieb

4 years ago

Can we use predictive models explainability for causal analysis ? I highly recommend this read, by @scottlundberg the author of SHAP approach bit.ly/34jJh2c

0 0 1 0 0

Sahbi Chaieb @sahbichaieb

4 years ago

Happy to see the rise of open source tools for AI models security inspection. Meet Counterfit from @Microsoft #MLSec #AIRedTeam bit.ly/3ef9yoi

0 0 0 0 0

Mark Riedl @mark_riedl

4 years ago

Hi all. Did you know @GeorgiaTech has launched a new, first-of-its-kind School of Cybersecurity and Privacy (scp.cc.gatech.edu). We are seeking to hire the first School Chair to lead it. Check out the job ad: tinyurl.com/gt-scp-chair (I’m chairing the search; DMs are open)

2 25 52 0 0

Download Image

Sahbi Chaieb @sahbichaieb

4 years ago

Honored to start the conversation on Machine Learning security with @TinyCyber at the DevSecOps track @DevOpSummit bit.ly/3dGoHP1 #MLOps #AISecurity

0 1 2 0 0

Sahbi Chaieb @sahbichaieb

4 years ago

Interesting thoughts on building a successful data-driven organization by @hassenchaieb

hassenchaieb @hassenchaieb

4 years ago

Interesting thoughts on building a successful data-driven organization by @hassenchaieb

0 2 2 0 0

0 1 2 0 0

Sahbi Chaieb @sahbichaieb

5 years ago

Accuracy remains the first goal, adversarial robustness comes second for most applications.

arXiv Daily @Arxiv_Daily

5 years ago

Accuracy remains the first goal, adversarial robustness comes second for most applications.

0 0 7 0 0

0 0 1 0 0

Sahbi Chaieb @sahbichaieb

5 years ago

Interesting piece on the vulnerabilities of pickle files by @ESultanik. It shows how pickle files can be used to execute harmful code or corrupt your models. #mlsecurity #aisecurity #python blog.trailofbits.com/2021/03/15/nev…

0 5 2 0 0

Sahbi Chaieb @sahbichaieb

5 years ago

Great news! This is going to be a great resource to learn how to secure ML workflows

OpenMined @openminedorg

5 years ago

Great news! This is going to be a great resource to learn how to secure ML workflows

2 64 159 0 17

Download Image

0 0 2 0 0

Tim Scarfe @ecsquendor

5 years ago

Really enjoyed this conversation and learned so much! There's good reason to believe neural networks look at very different features than we would have expected. Adversarial examples are still a bit of an unknown quantity and there is a lot of interesting research going on.