Research · curated 23 Jul 2026
Thematic review and gap analysis on AI security - GOV.UK
First reported www.gov.uk
Coverage timeline
Single-source research — first reported, latest, and curated coincide.
Why it matters
The DSIT/Lancaster review maps where AI and agentic-AI security research is thin, giving defenders and policymakers a prioritized view of underexplored risks such as agentic system security, model provenance, and AI supply-chain integrity.
The UK Department for Science, Innovation and Technology commissioned Lancaster University to conduct a PRISMA-based thematic review and gap analysis of peer-reviewed AI security research from January 2021 to January 2026, screening 9,109 publications into 12 themes including Autonomous Agent Security, Supply Chain Vulnerabilities, and Inference Time Security. The review identifies five key research gaps, notably around verifying AI data and model integrity, tracking third-party model provenance, bridging AI and traditional IT attack surfaces for agentic systems, and significant gaps in the cyber security of agentic-AI systems.