Alexis Carlier, Zainab Ali Majid

Building realistic defensive cybersecurity benchmarks. Asymmetric Security responds to real cyber incidents and therefore holds data not available in the public domain. We would like to work with MATS scholars to build realistic benchmarks grounded in these real cyber incidents.

Stream overview

Building Realistic Defensive Cybersecurity Benchmarks

Existing cybersecurity benchmarks lack realism, rarely testing how models behave in realistic security scenarios. This is especially challenging in cybersecurity because most relevant data is private.

Asymmetric Security responds to real cyber incidents and therefore holds data not available in the public domain. We would like to work with MATS scholars to build realistic benchmarks grounded in these real cyber incidents.

Mentors

Alexis Carlier
Asymmetric Security
,
Cofounder / CEO
SF Bay Area, London
Policy and Governance
Capability and Propensity Evaluations
AI Systems Security

Alexis is the co-founder and CEO of Asymmetric Security. He was previously an AI security fellow at RAND and part of the founding team of GovAI.

Read more
Zainab Ali Majid (Zainab)
Asymmetric Security
,
Co-Founder
SF Bay Area, London
Capability and Propensity Evaluations
AI Systems Security

Zainab is the co-founder of Asymmetric Security. She was previously a cybersecurity analyst at Stroz Friedberg, where she investigated some of the largest cybersecurity breaches of the past decade (e.g., Cambridge Analytica). She has also published at NeurIPS on AI cybersecurity evaluations. Zainab holds a master’s degree in Physics from Oxford University.

Read more

Mentorship style

1 hour weekly meetings by default for high-level guidance. We will respond within a day to async communication.

Fellows we are looking for

Essential:

  • Experience implementing AI model evaluations.

Preferred:

  • At least one year of professional software engineering experience.
  • Strong interest in AI cybersecurity.

Scholars can collaborate with other MATS scholars and can find collaborators on their own. Asymmetric Security staff may also engage deeply. 

Project selection

We will assign the project direction; scholars will have significant tactical freedom.

Streams

The Winter 2027 cohort offers a wide range of research streams led by experts across AI alignment, interpretability, governance, and safety. Each stream provides its own research agenda, methodology, and mentorship focus.

London
Empirical
Interpretability
London
Interpretability, Red-Teaming, Monitoring
London
Monitoring, Adversarial Robustness, Control, Model Organisms, Red-Teaming, Dangerous Capability Evals, Safeguards
New York City
Policy and Governance
Dangerous Capability Evals, Control, Strategy & Forecasting, Policy & Governance, Scalable Oversight, Agent Foundations
SF Bay Area
Empirical
Theory
Dangerous Capability Evals, Adversarial Robustness, Security, Red-Teaming, Scalable Oversight
London
Control, Scheming & Deception, Dangerous Capability Evals, Monitoring
Washington, D.C.
Policy and Governance
Policy & Governance, Strategy & Forecasting
Oxford
Theory
AI Welfare
SF Bay Area
Control, Model Organisms, Scheming & Deception, Strategy & Forecasting
SF Bay Area
Theory
Interpretability
Tübingen
Dangerous Capability Evals, Agent Foundations, Adversarial Robustness, Monitoring, Scalable Oversight, Scheming & Deception
SF Bay Area
Policy and Governance
Dangerous Capability Evals, Policy & Governance
New York City
Monitoring, Dangerous Capability Evals, Scalable Oversight, Safeguards
SF Bay Area
Policy and Governance
Strategy & Forecasting, Policy & Governance
Montreal
Agent Foundations, Dangerous Capability Evals, Monitoring, Control, Red-Teaming, Scalable Oversight
SF Bay Area
Control, Model Organisms, Red-Teaming, Scheming & Deception