Researchers have developed a new privacy-preserving technique called Ghost for location data. This method generates plausible but unlearnable trajectories, which are sequences of check-in data that degrade the accuracy of models attempting to predict future locations. Ghost achieves this by perturbing the data onto the real-trajectory manifold using a frozen trajectory language model, making it difficult for adversaries to reconstruct or learn from the original information. AI
IMPACT This privacy technique could enable safer sharing of location-based data for research and development.
RANK_REASON The cluster contains a research paper detailing a new technical method. [lever_c_demoted from research: ic=1 ai=1.0]
Read on arXiv cs.IR (Information Retrieval) →
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →
