HetCSS Experiment Data: HNSW-ORAM Benchmark Datasets

This dataset contains pre-built HNSW index files and query vectors for reproducing end-to-end experiments in the HetCSS project (Heterogeneous Confidential Similarity Search with ORAM protection). Contents: - sift1m: 1M vectors, M=64, dim=128 - laion100K: 100K vectors, M=64, dim=512 - tripclick: 1.5M vectors, M=128, dim=768 - msmarco_bert: 8.8M vectors, M=128, dim=768 Each dataset includes: - query.fvecs: Query vectors in fvecs format - index.bin: Pre-built HNSW index in binary format Usage: tar -xzf hetcss_experiment_data.tar.gz # This creates the data/ folder with the required structure