• Final NIST blog concludes US‑UK collaboration on privacy‑preserving federated learning. • Series tracks evolution from theoretical PET discussions to real‑world adoption. • Explores privacy attacks, mitigation strategies, and input/output privacy safeguards. • Guest insights cover scalability, implementation, and data‑pipeline challenges. • Highlights gaps: cross‑jurisdiction data handling and real‑world PPFL deployment. • Calls for further research to guide practical, policy‑aligned PPFL use.

Article Summaries:

  • NIST’s final blog in a series on privacy‑preserving federated learning (PPFL) marks the culmination of a US‑UK collaboration with the UK’s Responsible Technology Adoption Unit (RTA). The series, launched in December 2023, examined practical aspects of PPFL, including privacy‑attack mitigation, input/output protection, and scalability challenges highlighted by winners of the PETs Prize Challenges. NIST is now testing real‑world PPFL deployments through its PETs Testbed at the National Cybersecurity Center of Excellence. Looking ahead, the UK National Disease Registration Service and the US National Cancer Institute will jointly explore PETs for cross‑border research on rare pediatric cancers, supported by multiple US and UK agencies.

Sources: