UK AISI Control
This stream is for the Control sub-team of the UK AISI Red-team. The broader red-team focuses on stress-testing mitigations for AI risk, including misuse safeguards, control techniques and model alignment red-teaming, and the Control sub-team works on evaluating lab Control monitors and figuring out best practices in Control evaluations.
Stream overview
Projects could include:
- Improving the quality and diversity of simulated control environments so we can stress-test monitors more easily.
- Improving automated red-teaming of monitors, including running human experiments to determine where it's possible to replace humans.
- Working on safety cases for control and evaluating lab risk reports/creating best-practices for such reports.
Standard (1-2 hours of weekly 1:1s)
London
Indifferent
Indifferent
Mentors
Asa Strickland is a research scientist at the UK AI Security Institute working on AI control red teaming and model organisms of misalignment. He was previously a postdoc with Sam Bowman at NYU, did MATS with Owain Evans, and mentored for the MATS, SPAR and Pivotal fellowships. He got his PhD at the University of Edinburgh, supervised by Iain Murray.
Fellows we are looking for
We're looking for scholars with hands-on experience in machine learning and AI security, particularly those interested in adversarial robustness, red teaming, or AI safeguards.
Ideal candidates would have:
- Experience with large language models (training, fine-tuning, evaluation, or safety research)
- Strong technical foundations in ML, ideally with coding experience in PyTorch or Inspect - Interest in one or more of our three focus areas: misuse (securing systems against bad actors), alignment (ensuring AI systems behave as intended), or control (keeping AI systems under human control even when misaligned)
- A mission-driven mindset and curiosity about how AI security research can inform real-world policy and deployment decisions
- An ability to advocate for your own research ideas and work in a self-directed way, while also collaborating effectively and prioritizing team efforts over extensive solo work.
We welcome scholars at various career stages especially those who are eager to work on problems with direct impact on how frontier AI is governed and deployed.
- Prior control research publications.
- Excellent knowledge of cybersecurity.
- Work on safety cases and risk assessments.
Project selection
Scholars will choose from a set of predefined project directions aligned with our current research priorities, such as:
- Developing automated methods to test AI misuse safeguards
- Investigating data poisoning attacks and defenses
- Designing benchmarks for misuse detection across multiple model interactions
- Testing control measures for potentially misaligned AI systems
We'll provide initial direction and guidance on project scoping, then scholars will have autonomy to explore specific approaches within that framework.
Expect weekly touchpoints to ensure progress and refine directions.
If mentees have particular ideas they're excited about that they see as fitting within the scope of the team's work, they're welcome to propose them, but there is no guarantee they will be selected