Findings/adaptive-attacks-defeat-published-defenses

Attackers who adapt to a defense defeat most published prompt-injection defenses that reported near-zero success against static attacks.

Reportedmeasured6 evidence records from 6 independent sourcesassistant-drafted
Scope: what this does not show

Research defenses and research models. CaMeL-style architectural isolation was not among the defenses tested in the main adaptive-attack study. A September 2026 preprint extends adaptive-attack results to 2026 API models (ASR@10 of 93.8% on GPT-5.6-Luna and 45.0% on GPT-5.6-Terra, and 7.3% on GPT-5.6-Sol by transfer without training on it), with no confidence intervals reported. An October 2026 preprint reports, from its authors’ own tests, an attention-gate defense that held adaptive-attack success to low but non-zero rates.

Reported: Stated by one source and not yet corroborated or challenged.

Evidence

How it relates to other findings

supportsqualifiescontestssupersedes
ReportedCorroboratedQualifiedContestedSupersededRevalidate· node size = evidence records · columns group by topic

Select a finding to see how it relates to others. Arrows point from the newer finding to the one it supports, qualifies, contests, or supersedes.

Key questions that rely on this finding

Status history

  1. 2025-01-17ReportedUS AISI shows novel attacks raise hijack rates sharply. · record
  2. 2025-05-20CorroboratedGoogle DeepMind independently reports adaptive attacks above 90% on Gemini. · record
  3. 2026-09-25ReportedcorrectionThe 2025 US AISI and Google DeepMind entries did not test published defenses with near-zero reported success, and DeepMind shares authors with the primary study. 'The Attacker Moves Second' is the primary evidence; no independent replication is recorded yet. · record