Security Level 5

The AI Security tech lab charting the technical roadmap to SL5 optionality for frontier AI labs. SL5 Standard & building the 1st prototype SL5 Datacenter

[Security Level 5 @SL5TaskForce]

Join us for SL5Con on December 4th in Downtown San Francisco!

We’re hosting a one-day conference on nation-state security for AI, bringing together people from across the AI security space who are working on its hardest problems. It’ll be a day of panel discussions, talks and presentations, networking opportunities, and demos. Keep an eye out for our speaker lineup and programming.

Apply now at https://t.co/wVvLgy9we8 to secure your spot. The application takes less than 5 minutes and we encourage anyone working in or adjacent to AI security to apply.

[Security Level 5 @SL5TaskForce]

Our CEO went on @theinformation's AI Deep Dive podcast! Check it out for a quick intro to SL5 + in second half some short deep dives into: distillation, cryptography breaking and how that effects SL5, how release flows look under SL5. SL5 is also hiring security engineers and researchers! Come build the frontier of security! https://t.co/BR8OWq0R4V

[Lisa Thiergart @LisaThiergart]

I went on the information's AI Deep Dive podcast and talked about SL5! Thank you for having me @rocketalignment and @theinformation! It's time for the industry to build SL5! Logical controls by spring 2027, and then physical controls! Lfg!

First time doing something like this, apart from 1-2 misspeaks pretty happy with how it turned out! This was recorded 2w ago note for that time I say 'this week'.

[Security Level 5 @SL5TaskForce]

@hernanVmorfin not yet, right now still in standards development & implementation testing phase, but we want to see SL5 certifications be a thing in the near future! We highly welcome participation & collaboration on this -- including at our (not yet formally announced) SL5 Conference on Dec 4th, 2026 in SF! Please DM for how to get involved!

[Luis Cosio @luiscosio]

At @SL5TaskForce we're proposing formal verification controls for the SL5 Standard (https://t.co/HTNQze4Cav). They ask to name the parts that keep model weights secret, model the policy formally, and prove it where today's tools allow.

Open for public comment until Oct 24. We'd love your feedback 👇
https://t.co/wHcXN7svq2

[Ben Hayum @BenHayum]

This is the second major AI-enabled cyberattack in a month via this paper's attack methodology. When will be do something about it?

[Security Level 5 @SL5TaskForce]

We think of SenL as a way to close an ecosystem gap during the next 2+ years, where there does not (yet) exist a path to bring the large numbers of frontier AI staff into a gov clearance program. For ex. due to constraints such as throughput, time-delay, citizenship, international information access constraints, etc.

[Security Level 5 @SL5TaskForce]

Glad to see this! Our project on Sensitivity Levels (SenL) provides a possible approach for private industry personnel vetting to address such threats https://t.co/wOnrbqkWrA

[Senator Jim Banks @SenatorBanks]

China will stop at nothing to catch up in super intelligence. As we bring advanced SI into our military, we must protect it from insider threats.

[Security Level 5 @SL5TaskForce]

The SenL approach combines OSINT with gov intelligence collaboration, to create a version of vetting that takes the strengths of the US clearance program and adapts it to what could be executed at scale for the private AI industry.

[Security Level 5 @SL5TaskForce]

@francoisfleuret https://t.co/w94kecrPHI We are working on this!

[Security Level 5 @SL5TaskForce]

If you are an impact-driven AI Security Founder or Technical Lead looking to help make SL4 and SL5 a reality, this CG 2M pre-seed and 20M philanthropic seed funding round is a great place to start. We've made great experiences with them. Hit us up with questions!

[Lisa Thiergart @LisaThiergart]

To my talented founder-y friends asking how they can get involved in AI safety - this is your chance! Coefficient is offering 2M pre-seed and 20M seed to found ambitious AI safety initiatives. I've had a great experience working with them as my main funder over past years. 1/n

[Security Level 5 @SL5TaskForce]

3/n They've published a list of ideas on impactful things to build. Check it out to get inspired! https://t.co/xNDVofnAHR

[Security Level 5 @SL5TaskForce]

2/n The evaluation process is straightforward, and they aim to make funding decisions within a few weeks of receiving proposals.

Details and expressions of interest: https://t.co/St3uHbXZ9y

[Emily Oehlsen @EmilyOehlsen]

Today we’re launching Project Tailwind, a call for founders to start ambitious new AI safety initiatives: https://t.co/k5SoaXbuWk

We’re looking for great people to engage seriously with the risks of transformative AI, and to create the research, technologies, and institutions that will help humanity navigate them.

There are critical, basic problems that no one owns. Over the last several months, my team at @coeff_giving brainstormed ideas we’d be excited to fund if we could find a promising founder, and the list quickly grew to more than 200 entries. We’ve narrowed it down to our favorites, but we also expect the best founders to bring their own ideas:
https://t.co/88qE9bVrEy

We’re providing funding at three levels:
1️⃣ Pre-seed: $200k to $2m to develop an idea and build a team
2️⃣ Seed: $2m to $20m to launch and scale
3️⃣ Scale: $20m to $200m+ for proven teams to scale, or world-class teams to start

If you’re excited about something on our list, or you have another proposal for driving the field forward, you should get involved: https://t.co/8utEYbXYhx

There are more good projects than there are people to work on them. Please help us make that stop being true!

Also hi, I’m Emily! This is my first tweet. I lead AI and biosecurity grantmaking at @coeff_giving.

[Security Level 5 @SL5TaskForce]

3/n On the practical side, we now publish the full control set as an OSCAL profile, so the overlay imports straight into existing compliance systems. That plus other quality-of-life improvements came from feedback by orgs already running the overlay.
Check it out at:
https://t.co/q3NrxIlRhg

[Security Level 5 @SL5TaskForce]

1/n The SL5 Standard goes post quantum! The SL5 Standard v0.1.2.- https://t.co/8FKEBtg7ul is now live — the main substantive changes are: our Inter-facility encryptors are now required to implement post-quantum algorithms, with the specific algorithm selection deferred to current guidance, since that guidance is still moving.

[Security Level 5 @SL5TaskForce]

2/n We also tightened the Rule of Two for the two serial encryptor layers at each endpoint: the layers can no longer share a cryptographic hardness assumption.

[Security Level 5 @SL5TaskForce]

@Yogi_Brn @attestable Congrats Yogi! Looking forward to seeing great security work happen!

[Security Level 5 @SL5TaskForce]

Come to AI Village at DEFCON at 10:15-11:15am today for our talk and fireside on: "Prototyping SL5 AI Datacenters: How to train frontier AI when your adversaries (and employees) are evil super-geniuses" - deepdive on our Project MOAT!

[AI Security Forum @AISecurityForum]

What does it take to stand up a datacenter built to Security Level 5 (SL5) from the ground up? ⚡️ @LisaThiergart will discuss Project MOAT, an exploratory SL5 datacenter built as a live test range.

For session times & detail, check our conference app. #AISecurityForum