LLMs may be more vulnerable to data poisoning than we thought

Alan Turing Institute – Blog(UK) 9 Oct 2025 58

Emerging evidence that LLMs are more susceptible to data poisoning than previously understood raises supply chain risk questions for APS agencies deploying or procuring AI systems.

  • Alan Turing Institute, UK AISI, and Anthropic are collaborating to study LLM vulnerability to data poisoning attacks.
  • Data poisoning research has direct relevance for Australian agencies assessing AI supply chain and procurement risks.
  • The extracted text is a brief blog teaser with limited technical detail - full findings not yet available.
  • Monitor Australia's AISI and agencies assessing AI procurement risk may want to monitor the Turing Institute's forthcoming findings for implications on supply chain security and model assurance.
  • Consider AI governance and risk teams could consider whether current procurement and assurance frameworks adequately account for data poisoning as an attack vector in LLM-based systems.

Implications are AI-generated. Starting points, not advice — see methodology for how they're framed.

View original source