3 papers
cs.CR2026
HaloMark: A Spectral Threshold for Embedding-Vector Watermarking under C2PA
Tarun Sharma
Foundation-model embeddings are now a primary data asset, but the content-provenance machinery built for images and audio does not transfer to them. C2PA binds to an asset with a s…
cs.CR2026
When Global Gating Is Enough: Admission-Time Hubness Control in Anisotropic Vector Retrieval Systems
Prashant Kumar Pathak, Tarun Kumar Sharma
Vector hubness, where a few points become nearest neighbors of many queries, creates a poisoning risk in retrieval-augmented generation (RAG): one injected document can influence u…
cs.LG2026
IVF-TQ: Calibration-Free Streaming Vector Search via a Codebook-Free Residual Layer
Tarun Sharma
Approximate nearest neighbor (ANN) indexes deployed against streaming corpora silently lose recall over weeks. The standard diagnosis is distribution shift, but under shuffled-i.i.…