SOURCE-LINKED INTELLIGENCE

Poisoning Attacks on the PGM-index

arXiv · AI, language, vision and robotics · article · Sep 2, 2026 · UTC

The PGM-index (Ferragina and Vinciguerra, VLDB'20) is one of the most practical learned indexes, owing to its theoretical elegance and consistently strong empirical performance. It is built on optimal piecewise linear approximations (PLAs) that minimize the number of segments. In this paper, we ask how sensitive this optimal PLA itself is to poisoning attacks. We propose PGM-attack, an efficient poisoning attack that sequentially inserts adversarial keys to inflate the resulting number of segments, and we develop a method for deriving theoretical upper bounds on the number of segments attainab

Read original source ↗ Open in workspace

recordType: paper
region: Global

Evidence & attribution

arXiv · AI, language, vision and robotics · 2026-09-02T09:08:00.000Z

First collected: 2026-09-21T05:32:15.665Z. This is not the publication date.