AI安全训练营(AISB)是一个为期四周的强化项目，旨在帮助研究人员和工程师快速掌握AI系统的安全基础知识。该项目涵盖网络安全基础（密码学、网络）、AI基础设施安全（GPU、供应链安全）以及针对ML系统的攻击（数据集木马、模型提取）等内容。训练营将于2025年8月5日至29日在英国伦敦举行，所有费用将由主办方承担。项目包括理论学习、实践练习和专家交流，旨在培养参与者保护AI系统的能力。同时，该项目也在招募讲师、内容编写者和运营支持人员。

🔑AI安全训练营(AISB)是一个为期四周的强化项目，地点在伦敦，旨在提升研究人员和工程师在AI系统安全方面的技能，项目时间是2025年8月5日至29日。

💻课程内容分为三个部分：安全入门、AI基础设施的网络安全以及现代ML管道的攻击。参与者将通过动手实践、讲座、阅读漏洞报告和专家交流来学习。

👨‍🏫该项目也在招募讲师、内容编写者和运营支持人员。讲师需要具备相关主题的经验，内容编写者负责设计练习，运营支持人员负责项目运营。

🌍主办方将为参与者提供旅行、住宿、餐饮和签证方面的支持，确保他们能够全身心投入到学习中。

Published on June 1, 2025 7:47 PM GMT

tl;dr

We're excited to announce AI Security Bootcamp (AISB), a 4-week intensive program designed to bring researchers and engineers up to speed on security fundamentals for AI systems. The program will cover cybersecurity fundamentals (cryptography, networks), AI infrastructure security (GPUs, supply chain security), and more novel attacks on ML systems (dataset trojans, model extraction). This program will run in-person from 5th Aug to 29th Aug in London, UK. We will cover all expenses.

Apply here to participate in AISB before EOD AoE, 22nd June 2025.

We are also looking for instructors for parts of the program and staff to help with operations.

Summary

We are running a 4-week program designed to equip AI safety researchers and engineers with critical security skills. We hope you'll leave the program with a well-practiced security mindset that will help you work on impactful projects and make AI systems more secure.

The curriculum includes exercises designed to help you get hands-on experience with securing AI systems, while building and practicing the security mindset. This includes a mix of pair programming exercises, lectures, reading about public vulnerabilities, and chats with experts. 

This program is aimed at people who are at ~the start of their journey into security, and have working knowledge in ML (or are willing to brush up using the MLAB curriculum before the program). We encourage you to apply if you think you'll be a good fit regardless of checking all the boxes - if going on technical deep dives and trying to understand how systems work by peeling the layers of abstraction away excites you, we'd love to hear from you.

Content

The content is divided into roughly three sections - introduction to security, cybersecurity for AI infrastructure, and attacks on modern ML pipelines. The exercises are designed to give you hands-on experience with cybersecurity on both the offensive and defensive sides, as well as train your security muscles so that you are more effective at spotting and patching security holes.

Introduction to security - This includes introduction to cryptography and cryptanalysis, the basics of Linux security, and breaking network protocols.Securing AI infrastructure - This section covers topics especially relevant to AI security - containerization, a case study on supply chain security, application security, and SecOps.AI pipeline vulnerabilities - This includes attacks like model extraction, trojans, adversarial inputs, etc. on modern ML systems (image models, LLMs, multimodal models, and so on). We will also cover security considerations for applications that use ML models. This will be preceded by optional weekend exercises with pytorch.

Call for staff

We are also looking for more people to help us run the program:

Instructors - if you have experience working with any of the topics listed above and would be available for a (paid, full-time) position for some number of weeks in August, please apply here.Content writers - if you would like to help us design and develop the exercises, and are available for a (paid, part-time) position in June/July, please apply here.Operations support - if you have experience working on operations for similar projects and are available for a (paid, part-time) position in June - August, please apply here.Elders - if you have strong opinions on a program like this, or would like to share any bits of wisdom with us, I would love to chat - please reach out.

Logistics

Where - London, UKWhen - 5th Aug, 2025 - 29th Aug 2025
The last week is an optional (but highly recommended) capstone project
20 participantsWe will also be able to help you with:
travel supportaccommodationlunch and dinner on the weekdayshelp with visas

Apply

Apply here to participate before end of the day, 22nd June 2025 (anywhere on earth). We will evaluate applications on a rolling basis, but we aim to get back to everyone by 30th June 2025. Please apply earlier if you'd like a decision sooner, and highlight your deadlines in the application form.

FAQ

Who is this program for?

We would like applications from people who:

Care about AI safety and ensuring these systems are developed responsiblyHave experience working with deep learning (training models, running evals, etc.)Are comfortable working with PythonWill be able to be in London for 3-4 weeks, starting 5th AugSome cybersecurity background (having explored the field by yourself is the best indicator of interest)Have some experience with C/C++

If you're not sure if you check all of these boxes, but think you'll be a good fit for the program, please do apply!

What will an average day look like?

You'll start the day with a lecture or a deep dive into a significant vulnerability or exploit. After this, you will spend most of your time pair programming to work on the exercises, and reading relevant material. We will plan to wrap up the exercises by dinnertime, after which we'll have some additional reading material to prepare for the next day.

In the last week, you'll work on a capstone project with a mentor - this can be implementing a security solution, replicating a significant cyberattack (in a controlled environment), or trying to break into systems (again, with explicit permission).

What does the application process look like?

Fill out the application formComplete a simple coding testYou talk to one of us

What if I have other commitments?

The curriculum and the readings will likely not leave much time, so we would recommend not having other major time commitments during the bootcamp. Feel free to reach out if you'd like to discuss your specific circumstances.

Are there prerequisites?

Yes, we would recommend having a good background in deep learning (or going through the content for a program like MLAB or ARENA) and being comfortable with Python. We will also send an exercise to help you brush up on essentials a couple of weeks before the program starts.

Can I join for some sections but not others?

No, given we have limited spaces, we would be more excited to have participants who can commit to the entire three weeks of the program.

Which costs will you be covering for the in-person program?

We will help you with accommodation, travel, food, and visas if you need us to. No, roller-coaster rides are not included.

Discuss