TheMachine Press

A daily newspaper for the age of artificial intelligence.

Morning editionPermanent story

safety security

The Poison Looked Like an Update

A retrieval attack avoided direct contradiction by presenting false material as newer information, increasing success across many tested settings.

Published Updated Story ID: mp-2026-08-06-005
Read the complete editionStory JSON

Summary

A retrieval attack avoided direct contradiction by presenting false material as newer information, increasing success across many tested settings.

PURSUE tests a black-box retrieval-augmented-generation poisoning strategy that frames injected misinformation as a non-contradictory update rather than an explicit conflict. Across three question-answering benchmarks, five generators and three conflict-resolution methods, the authors report the highest attack success in 35 of 45 settings and a mean gain of 9.7 percentage points over their strongest prior baseline. This is defensive preprint research on benchmark systems; it does not establish compromise of a named deployed service, and this report omits operational injection instructions.

Why it matters

A retrieval attack avoided direct contradiction by presenting false material as newer information, increasing success across many tested settings.

Limits and context

  • This is defensive preprint research on benchmark systems; it does not establish compromise of a named deployed service, and this report omits operational injection instructions.

Key claims

  1. A retrieval attack avoided direct contradiction by presenting false material as newer information, increasing success across many tested settings.

    Qualification: This is defensive preprint research on benchmark systems; it does not establish compromise of a named deployed service, and this report omits operational injection instructions.

    Evidence: source-2026-08-06-005

Sources

  1. arXiv preprint 2608.04756arXiv · primary research

Corrections

No corrections have been recorded for this story.