Spatial Light Modulators For Information Processing: Applications And Overview

Ambs, Pierre; Otón, Joaquı́n; Millán, Marı́a S.; Jaulin, Albéric; Bigué, Laurent

doi:10.1063/1.2812301

Cited by 4 publications

(1 citation statement)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Also, scalars α and γ depend on the physical parameters of the system such as the lens powers and the distances between the optical components. In practice, the kernel K(x) can be implemented by a Spatial Light Modulator (SLM) [1] which is a programmable transmissive mask (Figure 2) or microfabrication [15] and aerosoljet printing [26] which result in a fixed mask but with much higher resolution and miniature size. Also, when high precision is not required, inkjet printing on transparent substrates is a low-cost option [22].…”

Section: Training An Optical Kernel For Preserving Privacymentioning

confidence: 99%

Privacy-Preserving Image Acquisition Using Trainable Optical Kernel

Sepehri,

Pad,

Frossard

et al. 2021

Preprint

View full text Add to dashboard Cite

Preserving privacy is a growing concern in our society where sensors and in particular cameras are ubiquitous. In this work, for the first time, we propose a trainable image acquisition method that removes the sensitive identity revealing information in the optical domain before it reaches the image sensor. The method benefits from a trainable optical convolution kernel which transmits the desired information while filters out the sensitive information. As the sensitive information is suppressed before it reaches the image sensor, it does not enter the digital domain therefore is unretrievable by any sort of privacy attack. This is in contrast with the current digital privacy-preserving methods that are all vulnerable to direct access attack. Also, in contrast with the previous optical privacy-preserving methods that cannot be trained, our method is data-driven and optimized for the specific application at hand. Moreover, there is no additional computation, memory, or power burden on the acquisition system since this processing happens passively in the optical domain and can even be used together and on top of the fully digital privacy-preserving systems. The proposed approach is generic and adaptable to different digital neural networks, and desired and sensitive content pairs. We demonstrate our new method for several scenarios such as smile detection as the desired attribute while the gender is filtered out as the sensitive content. We trained the optical kernel in conjunction with two adversarial neural networks where the analysis network tries to detect the desired attribute and the adversarial network tries to detect the sensitive content. We show that this method is able to reduce 65.1% of sensitive content when it is selected to be the gender and as the kernel is optimized, it only causes 7.3% reduction of the desired information content. Moreover, we reconstruct the original faces using the deep image reconstruction method that confirms the ineffectiveness of reconstruction attacks to obtain the sensitive content.

show abstract

Section: Training An Optical Kernel For Preserving Privacymentioning

confidence: 99%

Privacy-Preserving Image Acquisition Using Trainable Optical Kernel

Sepehri,

Pad,

Frossard

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

Patterned Photostimulation in the Brain

Anselmi

Banerjee

Albeanu

2015

Biological and Medical Physics, Biomedical Engineering

View full text Add to dashboard Cite

Privacy-Preserving Image Acquisition for Neural Vision Systems

Sepehri

Pad

Kundig

et al. 2023

IEEE Trans. Multimedia

View full text Add to dashboard Cite

The training phase of deep neural networks requires substantial resources and as such is often performed on cloud servers. However, this raises privacy concerns when the training dataset contains sensitive content, e.g., face images. In this work, we propose a method to perform the training phase of a deep learning model on both an edge device and a cloud server that prevents sensitive content being transmitted to the cloud while retaining the desired information. The proposed privacypreserving method uses adversarial early exits to suppress the sensitive content at the edge and transmits the task-relevant information to the cloud. This approach incorporates noise addition during the training phase to provide a differential privacy guarantee. We extensively test our method on different facial datasets with diverse face attributes using various deep learning architectures, showcasing its outstanding performance. We also demonstrate the effectiveness of privacy preservation through successful defenses against different white-box and deep reconstruction attacks.

show abstract

Spatial Light Modulators For Information Processing: Applications And Overview

Cited by 4 publications

References 7 publications

Privacy-Preserving Image Acquisition Using Trainable Optical Kernel

Privacy-Preserving Image Acquisition Using Trainable Optical Kernel

Patterned Photostimulation in the Brain

Privacy-Preserving Image Acquisition for Neural Vision Systems

Contact Info

Product

Resources

About