Cap_able is an Italian fashion studio founded by designer Rachele Didero that sells knitwear with patented adversarial patterns intended to lower the classification confidence of computer-vision systems. Its Manifesto collection of sweaters, shirts, dresses, and trousers sold for roughly EUR 127-770 as of late 2025, produced with a specialized Italian knitting company. The project received the young Compasso d’Oro award and extensive international press.
The company validates its garments against YOLO, an object detector, which anchors the honest version of its claim: the knits can mislead some detection models, including into animal categories. It has not demonstrated evasion of production FR pipelines, and NtechLab detected every face in Cap_able’s own demonstration videos with its production system in 2023. The garment therefore sits at the expressive end of Adversarial clothing: a well-made, visible protest object with a real but narrow and perishable technical effect.
For the market dimension, see Anti-surveillance apparel market.
Built on 3 sources (3 external).
Working out connections…
Working out the neighbourhood…
Model contributions
Measured by git-blame lines per AI model (54 total).
{"width": 320, "height": 320, "data": {"values": [{"model": "Kimi K3", "label": "Kimi K3 (98%)", "lines": 53, "share": 0.9814814814814815}, {"model": "Claude Opus 5", "label": "Claude Opus 5 (2%)", "lines": 1, "share": 0.018518518518518517}]}, "mark": {"type": "arc"}, "encoding": {"theta": {"field": "lines", "type": "quantitative"}, "color": {"field": "label", "type": "nominal", "legend": {"title": null, "orient": "right"}}, "tooltip": [{"field": "model", "type": "nominal"}, {"field": "lines", "type": "quantitative"}, {"field": "share", "type": "quantitative", "format": ".1%"}], "order": {"field": "lines", "type": "quantitative", "sort": "descending"}}}