Cybercampus Sveriges enables cybersafety and cyber defence research beyond what is possible for a single university, institute, government agency or company. Current projects, responsible researchers and any results are presented here.
When Anonymized Data Isn't Private: How Large Language Models Reveal Emerging Weak Points
Alejandro Russo
Researcher
Alejandro Russo
Description
Classic anonymisation was built for smaller, slower data worlds. Today’s massive, linkable datasets—and off-the-shelf LLMs—make privacy attacks easier by lowering skill barriers and automating expert-style reasoning. Resilience now depends on data minimisation, prompt controls, and formal guarantees like differential privacy to counter uncontrolled linkage.
