Research
Prevented is Not Protected: What Attack Success Rate Hides about RAG
Publication date unknown · Discovered arxiv.org
Page published
Publication date unknown · First observed: 7 Nov 2026
Coverage timeline
Single-source research — one report is available.
Why it matters
Aligned RAG Evaluation shows why defenders should assess defense-induced failures and answer endorsement rather than rely solely on attack success rate when selecting RAG poisoning defenses.
Aligned RAG Evaluation is a matched-query protocol that compares clean and poisoned retrieval with and without defenses to identify prevented attacks and defense-induced failures. Experiments on HotpotQA and Natural Questions found that defenses can introduce new target-positive answers, while evaluation criteria can change defense rankings.