Biosecurity Considerations of Controlled Human Infection Model Studies (OBG24-2)
Project Outline
This project seeks to evaluate the biosecurity risks associated with conducting controlled human infection model (CHIM) studies. Researchers on this project will conduct assessments of several key risks of conducting CHIM studies, identify and evaluate additional risks, explore how these risks apply to specific pathogens, and detail mitigation strategies for these risks. We expect much of this project will consist of expert interviews, literature reviews, and desk research to identify potential risks, assess the threat level of those risks, and determine the best mechanisms for mitigating them while retaining the many benefits of CHIM research.
Background & Motivation
This project seeks to evaluate the biosecurity risks associated with conducting controlled human infection model (CHIM) studies. Researchers on this project will conduct assessments of several key risks of conducting CHIM studies, identify and evaluate additional risks, explore how these risks apply to specific pathogens, and detail mitigation strategies for these risks. We expect much of this project will consist of expert interviews, literature reviews, and desk research to identify potential risks, assess the threat level of those risks, and determine the best mechanisms for mitigating them while retaining the many benefits of CHIM research. We expect the main deliverable of this project will be a white paper released by 1Day Sooner with the possibility of collaboration with additional organisations.
Project Outcome
Research Questions
A summary of research completed in this cycle was shared collaborators, which is now planned to be fed into a publication submitted for peer review.
During the project, the researchers will work on the following: 1. A risk assessment of the biosecurity risks of CHIM studies and the infrastructure necessary to conduct them. This will be done through methods such as reviewing the literature and speaking to experts, and will look both at risks that have already been identified and potential additional risks. 2. An evaluation of how these risks apply to specific pathogens and types of pathogens (e.g. advances in pathogen engineering may be higher risk for viruses than bacteria and for certain families of viruses over others). This should include a discussion of pathogen characteristics that increase risk. Researchers should focus first on respiratory pathogens with pandemic potential, such as influenza, SARS-CoV-2, and MERS-CoV, but, where relevant, should include considerations for other diseases such as those on CEPI’s priority pathogen list.), WHO’s priority pathogens list, and Disease X. 3. An evaluation of the relationship between the benefits and risks of CHIMs (briefly discussed in this Pandemic ethics accelerator report, but not deeply assessed yet). 4. A recommendation of methods of mitigating these risks while retaining, as much as possible, the benefits of CHIM studies. 5. A discussion of how this risk/benefit analysis might differ for CHIM studies conducted in LMICs. The main deliverable will be a resulting white paper. Project researchers are not expected to complete the white paper in the 8-week project period, and are welcome, but not expected to continue throughout the writing process alongside other co-authors. All work will be acknowledged through authorship. A list of experts to consult will be included in project briefing materials. Experts will be introduced and lined up in advance of the project start to minimise delay.
Project Collaborators
1Day Sooner; Coalition for Epidemic Preparedness Innovations (CEPI).
Eliciting the Biological Knowledge of AI Models (OBG24-2)
Project Outline
AI models might contain biological knowledge that could be misused, and recently a method was introduced that made these AI models "unlearn” this knowledge. This project will explore how various tools, like advanced prompting techniques, or an access to the Internet, might help these models regain this knowledge. Researchers will use methods such as understanding-based and behavioral evaluations of AI models, as well as scaffolding and prompt engineering of AI models. The key result of the research will be the final report, which will be shared with key stakeholders.
Background & Motivation
COVID-19 pandemic demonstrated that humanity is unable to contain new pathogens, and ill-prepared for new pandemics in the future. General purpose AI models, as well as AI tools capable of predicting pathogenic properties of viruses, are becoming more capable, so in the upcoming years they might be used for designing new pathogens. Actors might use these tools to deliberately start a new pandemic, or it might be a result of an accidental lab leak. A recent paper introduced a Weapons of Mass Destruction Proxy (WMDP) benchmark that measures knowledge of an AI model that is necessary for biological, cyber, and nuclear attacks. The biological part of WMDP benchmark focuses on knowledge necessary for developing and disseminating agents able to cause a pandemic. The paper also introduced a method for "unlearning" this knowledge that makes a model to "forget" this dangerous information. The authors demonstrated the effectiveness of this method by measuring an AI model performance without any additional capabilities, like an ability to browse the internet, access to scientific literature, or advanced prompting techniques. These tools tend to improve performance of AI models, and they might improve the performance of a model after it has unlearned hazardous knowledge. The preliminary experiment showed that they might improve model performance on the benchmark. This project can become a good first step in a career in AI biosecurity. Governments around the world, including the US, the UK, and the EU, are developing methods for evaluating biosecurity risks posed by AI models. This project might help to develop relevant expertise, portfolio, and to grow the right network.
Project Outcome
Research Questions
Initial research on an AI-Bio benchmark was created, and this project is now working towards future publications.
The main questions of the project: - Which scaffolding methods and affordances are effective for an AI model to acquire knowledge about biosecurity threats for a model with no such knowledge? - Whether such methods might be used to create a useful behavioral benchmark for AI models? As there are many tools that might improve performance of an AI model, there is a room for participants to choose which methods do they want to use in their research. The result of the research will be summarised into a report, which will be shared with experts and key stakeholders. Experts will be consulted before making any output public, and anything that might be an infohazard will be removed before publication.
Project Collaborators
Center for AI Safety (CAIS).
Analysis of Gaps and Opportunities for Improved Governance in High-Containment Laboratories in African Regions (OBG24-1)
Project Outline
This research project aims to understand the existing governance structure and gaps in managing high-containment level laboratories in the African region and identify actionable opportunities for improving governance. As a researcher on the project, you will research in one or more countries, depending on your experience and capacity, to understand the governance structure, which will include collecting and analyzing current regulations and policies governing the operations of high-containment labs in the study country/countries and identifying existing gaps and actionable opportunities for improving the governance. The research will prioritize countries with [IHR-JEE scores](https://extranet.who.int/sph/jee) of 1 - 3 level on Biosafety and Biosecurity. Aside from global impact, the research findings are expected to have a significant impact on regional efforts such as the Signature Initiative, African Union Panel on Emerging Technology (APET), African Biosafety Network of Expertise (ABNE), and national institutions such as NBA Kenya, KMLTTB, NBMA Nigeria, MLSCN, NBA Ghana, Biosafety SA, among others. As a researcher on the project, you will have the opportunity to conduct policy analysis, engage with practitioners where possible, and gain hands-on experience in Biorisk policy in Africa. This positions you to contribute positively to shaping governance and reducing the likelihood of catastrophic biological events.
Background & Motivation
As biotechnology and dual-use research continue to advance, there is a growing likelihood of intentional or unintentional catastrophic biological events stemming from the activities of high-containment biological laboratories. While experts recognize the importance of these labs for public health, they also stress the need for strict oversight and regulation to prevent the spread of pathogens into the environment. In Africa, biosecurity concerns are not always prioritized due to limited time and resources, and many scientists lack training in laboratory biosecurity and relevant international regulations. Despite the presence of few BSL-3 and BSL-4 labs in the region, the increasing economy, technology, and urbanization in most African nations make it likely that there will be an increase in the number of such labs in the future, emphasizing the importance of enacting appropriate regulations and oversight. Implementing effective policies and regulations on high-containment level facilities will mitigate and reduce risks from labs, providing long-term protection impact. The ultimate goal is to ensure that global catastrophic biological events arising from the activities of high-containment biological labs from the region are averted.
Project Outcome
Research Questions
A final report was produced, an abstract was accepted for oral presentation at the International Pandemic Sciences Conference 2024, and the project's findings will be disseminated to national and regional stakeholders, potentially feeding into lab safety practices.
Over the seven weeks, a researcher will contribute to answering some of these questions. Questions one, two, and three deal with specific countries, while questions four and five regionally. 1. What are the existing governance practices for managing the operation of high-containment level labs? Focusing on a specific country and understanding the context, such as which government institutions and their governance responsibility and mandates. If multiple institutions are involved, what governance responsibility exists within each? 2. What gaps exist in the current governance structure of high-containment levels labs? This will involve identifying lacking regulations, policies, or administrative measures; also, the question will seek to understand gaps within the regulatory institution. Are the institutions making the governance lacking? Are their issues with centralization or decentralization? Are the institution's capacity or resources constraints to make more effective governance? 3. What actional opportunities are available to strengthen and make governance more robust and effective? Researchers will justify with evidence what makes the recommendation actionable and explain how the recommendation connects to one or several gaps identified. 4. What regional organizations/institutions could shape and improve the governance, and in what ways? What's currently lacking? 5. What actional opportunities are available for the identified regional organization/institutions to strengthen and make governance more robust and effective? Researchers will justify with evidence what makes the recommendation actionable and explain how the recommendation connects to one or several gaps identified.
Project Collaborators
Governance for Survival Initiative (GSI).
Example Projects
We do not have any active projects running. Join our mailing list below to be notified of when our next cycle of projects is announced. For now, feel free to take a look at some of the projects we've run in the past. If you have ideas for projects you would like us to run, reach out to us at contact@oxfordbiosecuritygroup.com.
The Project Cycle
Every project is different, and exactly how a project progresses is ultimately down to the project lead. But overall, an OBG project cycle consists of the following stages.
1. Project Ideation
Before a project begins, we consult with our network, experts, potential collaborating organisations, and potential project leads to scope projects for the cycle. This ensures our projects are high-quality, suitable for OBG, and useful for researchers.
2. Project Recruitment
Once projects are in place, we will recruit for researchers, and occasionally for project leads and co-leads. Recruitment typically lasts a few weeks and consists of two rounds: an application form and a virtual interview.
3. Project Research
Every project is different, and exactly how a project progresses is ultimately down to the project lead. However, all projects will typically consist of a research question divided across the team; independent research, and regular meetings organised by the project lead.
4. Project Completion
Projects all result in different deliverables. However, most of our projects will result in a final presentation and final report shared directly with collaborating organisations. Some of our projects have continued in some form even after the cycle ends.
Project Ideation & Recruitment
Before a project cycle begins, we consult with our network, experts, potential collaborating organisations, and potential project leads to scope projects for the cycle. This ensures our projects are high-quality, suitable for OBG, and useful for researchers. OBG projects typically have a well-defined research agenda, but whether there is a specific research question will depend on the project.
Most projects will begin with a project lead and collaborating organisation, although this is not the case for every project. We select projects based on urgency, timing, prioritisation, the availability of suitable project leads, and the availability of suitable collaborating organisations. We will typically run between 5-7 projects per cycle.
Once projects are in place, we will recruit for researchers, and occasionally for project leads and co-leads. Recruitment typically lasts a few weeks and consists of two rounds: an application form and a virtual interview. We guide the project lead through this process.
Project Research
Every project is different, and exactly how a project progresses is ultimately down to the project lead. However, there are some commonalities across all our projects.
Week 1
In the first week, your project lead will usually hold an online meeting for the project onboarding. In this meeting you will receive more details on the project; final deliverables, and the structure of future meetings. The first week will also typically be dedicated to narrowing down the project scope; dividing research between project leads, and getting to know your fellow researchers.
Weeks 2 - Penultimate Week
The following weeks will typically involve independent research; regular meetings with the rest of the team, receiving feedback on your work so far, and contributing towards the final deliverable. We provide guidance and best practice to all project teams. However, this is the part of the project that varies the most: it is ultimately up to project leads what your day-to-day will look like.
Final Week
In the final week, you will typically finalise project deliverables, receive feedback, and your project lead will usually hold a final meeting to wrap-up the project.
Project Completion
Projects all result in different deliverables. However, an example of what the deliverables for a project might look like:
Midpoint Presentation: a presentation of all the research work so far, largely used to provide accountability, course-correct, and support researchers. It is typically just internal.
Final Presentation: a presentation summarising the research completed. Can be public or strictly internal.
Final Report: a report that summarises the research completed in more detail. This is not always a report however, and can be a presentation, blog post, article, or even publication.
These deliverables are usually shared with the collaborating organisation, and may be shared publicly.
Why take part?
OBG projects are very varied, and we think many types of people could benefit from participation in an OBG project. Students looking to explore biosecurity for the first time; recent graduates looking to upskill in biosecurity; experienced medical professionals looking to transition to biosecurity, and even more senior researchers looking to engage in an interesting, exploratory, project may all find participating in an OBG project worthwhile.
Short research projects can be a good way to test your fit; explore a topic you've never considered before; skill up in a specific area; learn more about an interesting topic, or gain research experience. In every project cycle, we aim for projects that serve a range of experience levels, career stages, and interests. Ultimately, provided you are willing and able to spend a few hours a week on your OBG project, an OBG project can be a flexible option for almost anyone.
Projects
Oxford Biosecurity group is centred around projects. Projects typically revolve around a research question or a small set of research questions. Over a number of weeks, usually no more than 12, project leads and researchers will work on producing project deliverables that address these questions.
Each project has an overarching goal, separated into specific research questions for a researcher to be working on. Outputs usually include a final presentation and a final report, and some projects have additional outputs. These final deliverables are typically shared with collaborating organisations, and may also be shared publicly.
We do not have any active projects running. Click below to see examples of some of the projects we've run in the past.
Key Info
Current Cycle Dates
There is currently no project cycle taking place.
Next Cycle Dates
We do not currently have the dates of our next cycle confirmed. Stay tuned or join our mailing list for the announcement!
Cycle Duration
Project cycles are typically 8-12 weeks long.
Requirements
We cater to a range of backgrounds and experience levels. See more information about our requirements here.