This is also a valid approach just not the approach used for the proof-of-concept. Many community and activist uses of CV Dazzle have targeted face recognition, instead of detection. Often these two algorithms are conflated, but they are entirely different, each with its own set of vulnerabilities. If a face is not detected by the algorithm, it effectively blocks the subsequent recognition algorithms. This is the strategy used for the looks on this page, which all target the Viola-Jones haarcascade face detection algorithm. Therefore, CV Dazzle could be used to block facial recognition by blocking face detection using only hair styling and makeup. Since face detection is the first step in any automated facial recognition system, blocking the detection stage also blocks any subsequent facial analysis including recognition and emotional analysis. Haarcascade frontalface-alt2 reverse face A visualization of process is shown in this By using makeup and hairstyling the dark and light areas can be reversed to lower the probability of detection through the various stages of the haarcascade profile, a multi-stage detector that uses around 20-25 stages of scoring during the detection process. The key observations are the heavy reliance on the dark areas around the eyes, the symmetry, the stability of the nosebridge, and the darkness under the nose. For over a decade, since the development of the Viola-Jones algorithm in 2003, these were the prototypical face appearances used to detect the human face in security videos. To guide the development of the initial looks for the project, a genetic algorithm was used to find the optimal faces hidden within the algorithm. Because computer vision is a probabilistic determination, finding the right look is about finding how to appear one step below the threshold of detection. Newer forms of a CV Dazzle approach could target other algorithms, such as deep convolutional neural networks, but would require finding vulnerabilities in these algorithms. Patterns and designs are always specific to the wearer, algorithm, and environmental conditions.ĭesigns can be created using only hair styling, makeup, and fashion accessories, which could be customized to any wearer’s style and are low-cost or free, and accessible to a wide audience. CV Dazzle is a camouflage strategy to evade computational vision systems that evolves, as camouflage does, alongside the technology it aims to subvert. But CV Dazzle is not a specific design or pattern. In the image above (Look #5), the design targets the Viola-Jones face detection algorithm, a popular (at the time of development) and open source face detector that is included with the OpenCV computer vision framework. The initial CV Dazzle designs work by altering the expected dark and light areas of a face (or object) according to the vulnerabilities of a specific computer vision algorithm. September 2020: Two new 3D-designed CV Dazzle looks presented at Designs forĭifferent Future Walker Center of Art (scroll down to related media).March 1, 2023: now redirects to this page where I maintain update and accurate information about the project.More technical information about reverse engineering and visualizing the vulnerabilities in the haarcascade and other computer vision algorithms may be published here in the future. This page is an overview of the project concepts, motivation, and initial tests. Commission for the New York Times Op-Art. All of sudden a key technology in the previously infallible post 9/11 security apparatus could be foiled by makeup and hairstyles.ĬV Dazzle Look 5. But until then it was the only face detection algorithm and therefore created a single point of failure when broken, cascading throughout the security industry. This algorithm gradually become deprecated in security around 2013-2016 and is no longer used, therefore the original patterns (designed between 2010-2013) are no longer active looks. In this proof of concept research project from 2010 the technique was used to break the widely-used (at the time) Viola-Jones face detection algorithm by using bold patterning to break apart the expected features of the face detection profiles (haarcascades). It is the first documented camouflage technique to successfully attack a computer vision algorithm. Unlike traditional camouflage, such as disruptive-pattern material, that hides the wearer from human observation, CV Dazzle is designed to break machine vision systems while still remaining perceptible to human observers. CV DazzleĬV Dazzle is a form of camouflage from computer vision created in 2010 as my masters thesis at New York University’s Interactive Telecommunications Program. Developed for Designs for a Different Future 2020 to break convolutional neural network face recognition.
0 Comments
Leave a Reply. |