Polymorphic Sybil RAG - Hijack Rate: leaderboard

Metric: Hijack rate (%; share of the 2,982 released HotpotQA and Natural Questions items; few-shot prompt shared byte-identically across readers, temperature 0, E5+cross-encoder retrieval, strict exact match against the canonicalized gold and target answer sets whose answer is the attacker-chosen target answer, lower is better; Forced Exposure: the six sybil passages placed at fixed top-10 positions beside gold-supporting passages). Source: arxiv.org. Saturation forecast: Around December 2026. 5 models tracked.

Top models

Interactive version: theaggregate.ai/benchmark?slug=polymorphic-sybil-rag-hijack-rate · How It Works · Data refreshed daily, snapshot 2026-09-29.