UK BUSINESS AI UNIVERSE: Safety: Programmes, tools and partnerships

Programmes, tools and partnerships

9 records Generated from this page's data. Click a name to open its panel on the Safety page. Records resting on one source are tagged "one source".

Record	What it is	Links	Confidence
AISI and Anthropic data-poisoning studyPartnerships and contracts	Joint study, which AISI calls the largest of its kind, showing small amounts of corrupted training data can plant hidden backdoors in models. published	aisi.gov.uk/blog	one source
AISI and Australian AI Safety Institute partnershipPartnerships and contracts	Wider partnership between the UK and Australian AI safety institutes; Australia is also an Alignment Project funder.	aisi.gov.uk/blog	one source
AISI and Google DeepMind research partnershipPartnerships and contracts	Research partnership covering shared data access, joint papers and alignment topics such as chain-of-thought monitoring.	aisi.gov.uk/blog	one source
AISI and Irregular cyber evaluation workPartnerships and contracts	Joint work showing recent AI models can make good use of 10–50 times larger token budgets on cyber tasks. published	aisi.gov.uk/blog/evidence-for-inference-scaling-	one source
AISI and Microsoft frontier AI safety partnershipPartnerships and contracts	Partnership with Microsoft on frontier AI safety; Microsoft is also a backer of the Alignment Project.	aisi.gov.uk/blog	one source
AISI evaluations bounty programmeSchemes, programmes and AI lines	AISI paid outside researchers for new evaluation tasks and agent scaffolding, expecting £3,000–£15,000 per successful task. closed	aisi.gov.uk/blog/evals-bounty	one source
AISI, Anthropic and OpenMined secure evaluation enclaves pilotPartnerships and contracts	Pilot by AISI, Anthropic and OpenMined of secure enclaves for evaluating AI models, cited in DSIT's assurance roadmap. piloted	gov.uk/government/publications/trusted-third-par	one source
ARIA Safeguarded AI programmeSchemes, programmes and AI lines · also on Labs	£59m ARIA programme funding safeguarded-AI research: 22 theory projects listed; a cybersecurity call is open until 31 October 2026. Profile Owner or parent ARIA (Advanced Research and Invention Agency), opportunity space "Trust Everything, Everywhere" Lab director or lead David "davidad" Dalrymple — Programme Director — Nov 2025 Other leaders Ant Rowstron — CTO, ARIA (quoted on the pivot, Nov 2025) What it does An ARIA programme building mathematical tools ("TA1") so that AI systems can be checked against formal models of the world and written specifications. In November 2025 ARIA changed course: it stopped funding a machine-learning organisation (TA2) and will instead grow TA1 into an open-source toolkit for mathematical assurance. A formally verified firewall for critical infrastructure is one example. A cybersecurity call is open. Research groups or focus TA1.1 Tooling (Theory); TA1.2 + 1.3 Tooling (Platform and human-computer interfaces); TA1.4 Sociotechnical Integration; TA2 Machine Learning Organisation (cancelled; had planned £18m for a non-profit); TA3 Real-World Applications, repurposed as an updated TA2 on applications (energy networks, clinical trials, telecommunications); Safeguarded AI: Cybersecurity (Track 1 Blue Teams, Track 2 Red Team) Notable outputs 22 TA1.1 theory teams listed, among them: SAINT: Safe AI ageNTs — Alessandro Abate, University of Oxford — active; ULTIMATE — Radu Calinescu, University of York — active; Employing Categorical Probability Towards Safe AI — Sam Staton, University of Oxford — active; Double Categorical Systems Theory for Safeguarded AI — David Jaz Myers, Topos Research UK — active; Hyper-optimised Tensor Contraction for Neural Networks Verification — Stefano Gogioso, Hashberg Ltd — active; Unified Automated Reasoning for Randomised Distributed Systems — Alexandra Silva, UCL and Cornell — active; Event Structures as World Models — Alex Kavvos, University of Bristol — active; Profunctors: A unified semantics for safeguarded AI — Nicola Gambino, University of Manchester — active; Learning-Theoretic AI Safety — Vanessa Kosoy, ALTER — closed Funding or budget as published £59m — read 31 Oct 2026 — https://aria.org.uk/opportunity-spaces/mathematics-for-safe-ai/safeguarded-ai/funding (also on the funded-projects page) Partners named funded organisations above, plus University of Edinburgh, UCL, University of Southampton/Heriot-Watt, University of Strathclyde, Glasgow Lab for AI Verification, University of Pisa, Tallinn University of Technology, University of Birmingham, University of Sussex, University of Kent (TA1.1 teams) Uk government links ARIA programme Status now Active: the Cybersecurity Track 1 rolling call had a proposal cut-off on 31 Oct 2026, with applicants told by 30 Nov 2026. Labs Round 8 deep profile (31 Oct 2026), as the researchers wrote it; confidence: verified (three ARIA pages). Sources aria.org.uk/opportunity-spaces/mathematics-for-s aria.org.uk/insights-1/ai-progress-and-a-safegua aria.org.uk/opportunity-spaces/trust-everything-	aria.org.uk/opportunity-spaces/mathematics-for-s · aria.org.uk/opportunity-spaces/trust-everything- · aria.org.uk/insights-1/ai-progress-and-a-safegua · aria.org.uk/programme-safeguarded-ai/	verified
UK–Germany joint statement on advanced AI safety and securityPartnerships and contracts	Joint statement by the UK and Germany on the safety and security of advanced AI, published by AISI. published	aisi.gov.uk/blog	one source