Over the past decade, digital cameras have been widely adopted in various aspects of our society, and are being massively used in mobile phones, security surveil­lance, autonomous vehicles, and facial recog­nition. Through these cameras, enormous amounts of image data are being generated constantly, which raises growing concerns about privacy protection. Some existing methods address these concerns by applying algorithms to conceal sensitive infor­mation from the acquired images, such as image blurring or encryption.

However, such methods still risk sensitive data exposure because the raw images are already captured before they undergo digital processing to hide or encrypt the sensitive information. Also, the computa­tion of these algorithms requires addi­tional power consumption. Other efforts were also made to seek solutions using customized cameras to downgrade the image quality so that identi­fiable information can be concealed. However, these approaches sacrifice the overall image quality for all the objects of interest, which is undesired, and they are still vulnerable to adver­sarial attacks to retrieve the sensitive information that is recorded.

Now, researchers of University of California, Los Angeles, demons­trated a new paradigm to achieve privacy-preserving imaging by building a funda­mentally new type of imager designed by AI. The group, led by Aydogan Ozcan, presented a smart camera that images only certain types of desired objects, while instan­taneously erasing other types of objects from its images without requiring any digital processing.

This new camera design consists of successive trans­missive surfaces, each composed of tens of thousands of diffractive features at the scale of the wavelength of light. The structure of these trans­missive surfaces is optimized using deep learning to modulate the phase of the trans­mitted optical fields such that the camera only images certain types/classes of desired objects and erases the others. After its deep learning-based design, the resulting layers are fabri­cated and assembled in 3D, forming the smart camera. After its assembly, when the input objects from the target classes of objects appear in front of it, they form high-quality images at the camera's output. In contrast, when the input objects in front of the same camera belong to other undesired classes, they are optically erased, forming non-infor­mative and low-intensity patterns similar to random noise.

Since the charac­teristic information of undesired classes of objects is all-optically erased at the output through light diffrac­tion, this AI-designed camera never records their direct images. Therefore, the protection of privacy is maximized since an adver­sarial attack that has access to the recorded images of this camera cannot bring the information back. This feature can also reduce cameras' image storage and trans­mission load since the images of undesired objects are not recorded.

To experi­mentally demonstrate this unique data-specific camera, the research team designed it to specifically and selec­tively image only one class of handwritten digits, and fabricated the designed camera using 3D printing. This 3D fabri­cated camera was tested using terahertz waves illumina­ting handwritten digits. Following the core principles of its design, the smart camera was able to selectively image the input objects only if they were handwritten digits “2”, while instan­taneously erasing all the other handwritten digits from the output images, yielding low-inten­sity noise-like features. Furthermore, the research team rigorously tested their camera design under varying lighting conditions that were never included in its training, and showed that this smart camera is robust to such variations in illu­mination.

Beyond data class-specific imaging, this AI-based camera design can be used to build encryption cameras, providing an additional layer of security and privacy protection. Such an encryp­tion camera, designed using AI-optimized diffractive layers, optically performs a selected linear transformation exclusively for the target objects of interest. Only those with access to the decryption key (i.e., the inverse linear trans­formation in this case) can recover the original image of the target objects. On the other hand, the information of the other undesired objects is irre­versibly lost since the AI-designed camera all-optically erases them at the output.

Therefore, even if the decryption key is applied to the recorded images, it yields noise-like features for other classes of undesired objects. Except for the illu­mination light, this smart camera does not require any external power for its computation and operates at the speed of light. Therefore, it is fast, data- and energy-efficient, making it especially suitable for task-specific, privacy-aware, and power-limited imaging appli­cations. The core teachings of this diffractive camera design can inspire future imaging systems that consume orders of magnitude less computing and data trans­mission power. (Source: LPC-CAS)

Reference: B. Bai et al.: To image, or not to image: class-specific diffractive cameras with all-optical erasure of undesired objects, eLight 2, 14 (2022); DOI: 10.1186/s43593-022-00021-3

Link: Ozcan Research Group, University of California, Los Angeles, Los Angeles, USA