AI Detector Robustness: Data and Methods from Our RAID Reanalysis
Full aggregate tables from Violet's RAID reanalysis: detector accuracy under 11 attacks, per-document flip rates, per-domain false positives, methods.
Loading
VioletTag
7 postsfiled under “original research.”
Full aggregate tables from Violet's RAID reanalysis: detector accuracy under 11 attacks, per-document flip rates, per-domain false positives, methods.
Measured on 480,000 generations: paraphrasing makes one detector 5.4pp more accurate and another 17.0pp worse. Evasion is a detector lottery, not a strategy.
One pooled 5% setting, eight writing domains of truth: measured per-domain detector false-positive rates range 0.96% to 20.4%.
Measured on 480,000 generations: one symbol substitution flips 93.7% of a detector's per-document verdicts. Aggregate accuracy hides the collapse.
A decision-first framework for choosing growth metrics without mistaking publishing, rankings, or TVL for attention, adoption, or customer value.
A practical operating system for translating meaningful product changes into clear explanations, useful distribution, measurable action, and market learning.
A practical system for deciding which public surfaces a consumer-crypto product should maintain, repair, consolidate, or deliberately decline.
Turn social and market signals into an ecosystem-growth, go-to-market, or technical engagement built around the work your team needs.
Explore engagements