Camouflage projects

An anonymously operated shop selling hoodies, shirts and masks it describes as carrying engineered adversarial patterns, citing published techniques including Expectation over Transformation and the ImageNet-Patch dataset. It claims effects on face recognition, object detection and multi-object tracking, which is the widest claim set among comparable sellers. No test results, target models or imagery of a detector failing are published, and the shop discloses no company name, location or team.

“Face/Off: Adversarial Drag in the Age of Capture” is a Queer and Feminist Informatics Network workshop at the University of Amsterdam. Drag and makeup experiments challenge face and gender classification. It claims no effectiveness against a named system.

Kate Bertash’s garments carry plausible number plates to inject false records into licence-plate databases, not hide faces. Demonstrated at DEF CON 27 against OpenALPR and commercial mobile readers; garments have not been sold since around 2023.

Open-source code from the EAVISE group at KU Leuven that generates a printable patch optimised against a person detector's own objectness loss, so that a person holding it produces no detection proposal. Published results against YOLOv2 on the INRIA test set report recall falling from 100 per cent to 26.5 per cent with the best patch, at a patch of roughly 40 centimetres held facing the camera. The authors note that patches transfer poorly to different detector architectures; because it is a generator rather than a fixed pattern, it can be retrained against a current model.

An online shop selling garments, gaiters and masks printed with patterns the seller describes as chosen to disrupt computer-vision systems. The shop's own wording is that the images are “thoughtfully crafted, designed, and selected”, and its founder told the Mozilla Foundation that the designs are tested informally against a TensorFlow model and that he is “not saying it will always work”. In Mozilla's hands-on review the garments avoided a consumer camera's human-detection alert but did not defeat a pose-estimation model.

Milan-based fashion company making knitted patterns intended to disrupt person and object detection, before face matching.

Adam Harvey’s makeup and hairstyling experiments targeted Viola-Jones Haar-cascade face detection. These historical patterns do not establish protection against modern neural networks.

Sterling Crispin used genetic algorithms to generate forms that face-analysis systems read as face-like, then 3D-printed wearable masks. Produced in 2013–2015, the artwork examines machine representations; it is not presented as a countermeasure.

Michelle Tylicki and Lauri Love’s interactive salon teaches and tests anti-surveillance makeup with model feedback. Public documentation lacks a complete reproducible benchmark.

Simon Weckert’s shirt and artwork uses a pattern developed against YOLO person detection. The artist does not promise anonymity or effectiveness against government systems.

Zach Blas’s workshops combine participants’ facial data into collective masks. The performances challenge biometric classification and its social biases.

Betabrand and Chris Holmes’ 2015 collection used glass-nanosphere fabric to reflect camera flash toward the lens. It targeted press photography and made no face-recognition claim. The crowdfunded collection shipped and is no longer sold.

Nick Bild's open-source build sews 940-nanometre infrared LEDs into a hat to overwhelm the photodiodes of infrared-sensitive cameras. The 940-nanometre choice produces almost no visible glow, so the wearer does not appear conspicuous to onlookers, which the project states as a design goal for protest use. Code, schematic and parts list are published; like all infrared flooding it depends on the camera passing near-infrared, so a daytime infrared-cut filter removes the effect.

Adam Harvey and Hyphen-Labs’ textile places false-face decoys around the wearer. The first version targeted OpenCV Haar cascades, was never sold and was not tested against modern deep face detectors.

Ewa Nowak’s brass face jewellery places discs below the eyes and a rectangle between them to disturb landmark detection. The only reported test was the absence of Facebook tag suggestions on frontal photos. No quantitative evaluation or commercial production is reported.

Hand-built caps sold from the Czech Republic with a nine-LED infrared strip in the brim, powered by two AAA cells for twelve to fourteen hours. They were intended to wash out the wearer's face for cameras sensitive to near-infrared in low light, and no wavelength, radiant power or test data was ever published. The maker's domain ceased to be associated with the product in November 2019; the listing survives as a product record and unbranded copies circulate on marketplaces.

Bill Swearingen’s evolutionary search for adversarial patterns printable on fabric. Presented at DEF CON as a recognition-pipeline experiment, it is moving toward a crowdfunded garment.

National Institute of Informatics research on infrared emitters and passive reflective or absorbing eyewear intended to suppress eye-region contrast. NII lists it as a past project.

Simone C. Niquille’s shirts use celebrity impersonators and stock faces to introduce false identities into social-media tagging. They explore database noise rather than hiding the wearer’s face.

Eyewear combining infrared-blocking lenses and reflective frames. Models target infrared illumination, eye tracking or depth mapping; effects depend on the camera spectrum and capture system.

An American eyewear brand selling frames with what it describes as passive optical filtering of specific infrared wavelengths. The stated aim is to reduce the accuracy and consistency of camera-based face recognition rather than to prevent it; the company's published evidence is that iPhone Face ID “did not consistently unlock” in its own internal testing. Several of the uses it names, such as retail and event scanning, are visible-light systems that an infrared filter would not be expected to affect.

Adam Harvey’s 2013 silver-plated garments reduced thermal signatures in long-wave infrared imaging. They address thermal observation, not face recognition. Previously sold through the Privacy Gift Shop; now sold out.

Dutch designer Jip van Leeuwenstein made a transparent moulded mask at the Utrecht School of the Arts in 2017 that bends and refracts light across the face, with the stated aim of preventing a camera from recovering accurate facial geometry while people can still read the wearer's expressions. The designer hedges the claim to “some forms of facial recognition” and publishes no test, target system or material specification. Snopes rated the widely shared claim that it blocks recognition from all angles as “Mixture”, finding it unclear whether the mask was ever produced or remained a thought experiment.

Mac Pierce’s DIY hood uses infrared emitters and strobing to disturb night-vision exposure. It targets camera capture, not face descriptors; effects depend on camera, distance, lighting and exposure controls.

London collective using CV Dazzle walks, workshops and films to examine public surveillance. It offers a workshop practice, not controlled evidence of recognition evasion.

A retroreflective scarf by Saif Siddiqui whose woven reflective elements return a camera flash toward its source, overexposing the wearer in the resulting photograph. The product targets flash photography on consumer devices and the brand makes no face-recognition claim; it has no effect on ambient-light photography, on closed-circuit cameras or on any recognition pipeline. A retroreflective surface also increases the wearer's visibility to infrared-illuminated cameras at night.

A 2016 prototype by Becca Ricks and Shir David placing 22 infrared LEDs around the bill of a baseball cap, with a potentiometer to vary brightness, to saturate a camera sensor over the wearer's face. The makers ran surveillance footage through the Google Cloud Vision API and reported that the wearer went undetected while an unprotected face in the same frame was detected. It was a single informal trial with no stated distances or light levels, and no build files were released.

Leipzig label selling Faception garments with face-like decoys, alongside reflective clothing and Faraday accessories. The face patterns aim to trigger false detections around the wearer.

Leonardo Selvaggio’s prosthetic and paper masks reproduce his face for multiple wearers. The artwork explores identity substitution rather than invisibility.

Privacy sunglasses sold by an undisclosed operator, built around a lens the company calls GLX or Green Light Lens technology. The marketing claims disruption of infrared recognition, visible-light recognition and thermal imaging; only the infrared claim has a conventional physical basis, since a tinted lens leaves the jaw, nose and head geometry fully imaged by a daylight camera and does not change the thermal emission of skin. No wavelength data, rejection curve or test results are published.

Jing-cai Liu’s 2017 design uses a head-mounted projector to change facial appearance. It is speculative: no optical specifications or test results are published, and the project says most designs are not working products. Often misattributed to collaborator Jip van Leeuwenstein.

A Montreal print-on-demand shop run by Jennifer Wu, selling apparel and accessories marketed to privacy and anti-surveillance audiences. Unlike comparable sellers it makes no technical claim about how its prints affect any system, presenting the range as protest and gift merchandise. Mozilla's review found the garments avoided a consumer camera's human-detection alert but not a pose-estimation model.

A lens coating sold by the mass-market optician Zenni, which the company says reflects up to 80 per cent of near-infrared light between 700 and 1050 nanometres. It targets the acquisition stage of infrared-based systems such as phone face unlock and infrared-illuminated cameras, not visible-light face matching. Zenni states that it does not guarantee anonymity or total protection, and independent testing by 404 Media found the lenses block infrared while leaving an ordinary daylight photograph fully usable for matching.