jhasomesh's profile picture. Professor of Computer Science and a music lover. Interested in formal methods, security, and Trustworthy ML. Oh yes, and classical music and jazz.

Somesh Jha

@jhasomesh

Professor of Computer Science and a music lover. Interested in formal methods, security, and Trustworthy ML. Oh yes, and classical music and jazz.

Fantastic course @zicokolter Looking forward to the materials.

I'm teaching a new "Intro to Modern AI" course at CMU this Spring: modernaicourse.org. It's an early-undergrad course on how to build a chatbot from scratch (well, from PyTorch). The course name has bothered some people – "AI" usually means something much broader in academic…



Excellent opportunity.

Please share widely. The UW–Madison ECE Department is recruiting at the assistant, associate, or full professor in foundational AI and machine learning tinyurl.com/4kwh8mvm



Happy Diwali to all. May this coming year be full of joy and prosperity.


Congrats Kirthi.

Congratulations to Kirthevasan Kandasamy, who received a 2025 @NSF CAREER Award. Kandasamy researches the incentives/dynamics at play when organizations share data and uses ML to ensure honest, equitable collaboration. Learn more: cs.wisc.edu/2025/10/15/kir…



Impressive work from @GoogleDeepMind

I am proud to share the announcement about our CodeMender project at @GoogleDeepMind, an agent that can automatically fix a range of code security vulnerabilities. From only a modest-compute run, our agent submitted 72 high-quality fixes to vulnerable code in popular codebases,…

ralucaadapopa's tweet image. I am proud to share the announcement about our CodeMender project at @GoogleDeepMind, an agent that can automatically fix a range of code security vulnerabilities.  From only a modest-compute run, our agent submitted 72 high-quality fixes to vulnerable code in popular codebases,…


Really stoked about this membership inference!

Our paper, "What Really is a Member? Discrediting Membership Inference via Poisoning" arxiv.org/abs/2506.06003 was accepted to NeurIPS! Great work by Neal Mangaopar, @AshishHoodaCS, @jhasomesh, @atulprakash, @UMichCSE, and @lzhuoh! #AI #privacy



I am seeking papers on comparing AI for attacks to AI for defenses--how attackers and defenders benefit from AI. Pointers welcome. Here are some sample questions along those lines. [1] Can AI be used by attackers to write exploits quicker? [2] Can AI be used by defenders to…


Amazing opportunity in a very strong team.

At Google DeepMind, we are excited to grow our Security & Privacy Research Team! If you are an exceptional researcher or engineer in security & privacy or machine learning, apply to one of the following: - RS, Tech Lead, AI Based Cyberattack Defense - RS, AI for Secure Code -…



This is inspiring, Adriana. Changing roles is not easy. Kudos to you for taking the plunge.

I recently quit a beloved engineering leadership role to become an IC at DeepMind. I want to become an expert again. the first time I was an expert, I worked my way up. now I'm starting over, but with more to prove & lose. it's terrifying and exhilarating at the same time



Congrats, Greg!

📢I'm joining NYU (Courant CS + Center for Data Science) starting this fall! I’m excited to connect with new NYU colleagues and keep working on LLM reasoning, reliability, coding, creativity, and more! I’m also looking to build connections in the NYC area more broadly. Please…

gregd_nlp's tweet image. 📢I'm joining NYU (Courant CS + Center for Data Science) starting this fall!

I’m excited to connect with new NYU colleagues and keep working on LLM reasoning, reliability, coding, creativity, and more!

I’m also looking to build connections in the NYC area more broadly. Please…
gregd_nlp's tweet image. 📢I'm joining NYU (Courant CS + Center for Data Science) starting this fall!

I’m excited to connect with new NYU colleagues and keep working on LLM reasoning, reliability, coding, creativity, and more!

I’m also looking to build connections in the NYC area more broadly. Please…


Congrats Laurens.

A new chapter: I am excited to share that I have recently joined Anthropic as a member of technical staff. Anthropic is a unique company with an even more unique mission that I am thrilled to be working towards. I will continue to be based out of NYC. Onwards!



Maksym is fantastic! If you are interested in AI safety, definitely apply.

🚨 Incredibly excited to share that I'm starting my research group focusing on AI safety and alignment at the ELLIS Institute Tübingen and Max Planck Institute for Intelligent Systems in September 2025! 🚨 Hiring. I'm looking for multiple PhD students: both those able to start…

maksym_andr's tweet image. 🚨 Incredibly excited to share that I'm starting my research group focusing on AI safety and alignment at the ELLIS Institute Tübingen and Max Planck Institute for Intelligent Systems in September 2025! 🚨

Hiring. I'm looking for multiple PhD students: both those able to start…


Thanks for hosting me @SimonsInstitute The audience interaction was fantastic~

2/2 Somesh Jha (@jhasomesh) spoke of the need to view the safety of ML through the lens of security and cryptography at the Simons Institute's workshop on Theoretical Aspects of Trustworthy AI. Video (Part II): simons.berkeley.edu/talks/somesh-j…

SimonsInstitute's tweet image. 2/2 Somesh Jha (@jhasomesh) spoke of the need to view the safety of ML through the lens of security and cryptography at the Simons Institute's workshop on Theoretical Aspects of Trustworthy AI. Video (Part II): simons.berkeley.edu/talks/somesh-j…


Loading...

Something went wrong.


Something went wrong.