The best single-track infosec + ML conference out there. If you're in that niche, you should be checking this out.

The Databricks AI Security Framework is also in our new AI Security page on our Trust Center databricks.com/trust/ai-secur…
Congratulations Arun Pamulapati for producing DASF, and thank you to all the reviewers and contributors including greats like Matei Zaharia Hyrum Anderson Ebrima N. Ceesay 🔴⚪️

Now available for ACM Members: 'Not with a Bug, But With a Sticker: Attacks on Machine Learning Systems and What to Do About Them' audiobook, by Ram Shankar Siva Kumar & Hyrum Anderson. A team of distinguished adversarial ML researchers deliver an account of the most... share.percipio.com/cd/Hky59bsMS

Our self-identity is influenced by the labels and roles we take upon ourselves.

Father, mother, teacher, geek, athlete, artist, loser, failure, etc.

Seek good roles. Be thoughtful in how you label yourself.

We're proud to co-author an update to National Institute of Standards and Technology's 'Adversarial Machine Learning: A Taxonomy and Terminology of Attacks and Mitigations' report, which includes security of LLMs.

This report is the result of incredible work by Apostol Alina Oprea Alie Fordyce Hyrum Anderson 👏

🚀 Exciting to present 'Tree of Attacks: Jailbreaking Black-Box LLMs Automatically' 📑🌳 Unlock the power of automated jailbreaks using Tree of Attacks with Pruning (TAP). arxiv.org/abs/2312.02119

Excited to announce that Simon Suo and I are featured in Forbes 30U30 2024! 🎉

It's been a wild year, and we couldn't have done this without our community, partners, investors, and of course our wonderful LlamaIndex 🦙 team.

forbes.com/30-under-30/20…

I am honored to be selected as this year’s Forbes 30 Under 30!
This is a recognition of the work everyone at Robust Intelligence has put in, and of the importance of the problems in AI Security we’re tackling.
Excited for the many years ahead!

I'm looking for PhD students or postdocs to sign a letter supporting me in case I get fired as CEO of my lab.

If that sounds fun, consider applying! (we might also do cool research)

If you miss the AI Center deadline, you can apply to my group directly: spylab.ai/hiring/

Our SaTML Conference LLM Capture-the-flag is now live!
Can you find successful defenses and attacks for prompt injection?

ctf.spylab.ai

On Thursday, November 16th, Unusual investor Allison Averill will host a fireside chat on securing AI with Hyrum Anderson, CTO of Robust Intelligence.

Register here: bit.ly/3FXwXHF

Allison and Hyrum will explore the following questions around securing AI:

➡ What are the

...and coming to audiobook later this month! :)

All author proceeds to charities!

❌Myth: #AI and #ML systems are immune to cybersecurity threats.

As we close out #CybersecurityAwarenessMonth , save 35% off 'Not with a Bug, But with a Sticker' by Ram Shankar Siva Kumar and Hyrum Anderson using code 'CYB35' below.

👉ow.ly/gKjB50Q0NG7

If you enjoyed the ML Model Attribution Challenge that Hyrum Anderson hosted last year, you might like this Kaggle competition:

kaggle.com/competitions/h…