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
VioletResearch
Research and operating notes on ecosystem growth, go-to-market execution, and growth engineering for crypto/Web3, AI and developer tools, and consumer fintech.
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 research-backed framework for choosing creator capabilities, building a complementary portfolio, and testing each role against a defined growth outcome.
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.
Why synonym shuffling cannot guarantee clean provenance—plus RAID measurements of 11 attacks collapsing AI detectors, and Violet's integrity protocol.
Turn social and market signals into an ecosystem-growth, go-to-market, or technical engagement built around the work your team needs.
Explore engagements