Light Lies: Optical Adversarial Attack
- URL: http://arxiv.org/abs/2106.09908v1
- Date: Fri, 18 Jun 2021 04:20:49 GMT
- Title: Light Lies: Optical Adversarial Attack
- Authors: Kyu-Lim Kim, Jeong-Soo Kim, Seung-Ri Song, Jun-Ho Choi, Chul-Min Joo,
Jong-Seok Lee
- Abstract summary: This paper introduces an optical adversarial attack, which physically alters the light field information arriving at the image sensor so that the classification model yields misclassification.
We present experiments based on both simulation and a real hardware optical system, from which the feasibility of the proposed optical attack is demonstrated.
- Score: 24.831391763610046
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: A significant amount of work has been done on adversarial attacks that inject
imperceptible noise to images to deteriorate the image classification
performance of deep models. However, most of the existing studies consider
attacks in the digital (pixel) domain where an image acquired by an image
sensor with sampling and quantization has been recorded. This paper, for the
first time, introduces an optical adversarial attack, which physically alters
the light field information arriving at the image sensor so that the
classification model yields misclassification. More specifically, we modulate
the phase of the light in the Fourier domain using a spatial light modulator
placed in the photographic system. The operative parameters of the modulator
are obtained by gradient-based optimization to maximize cross-entropy and
minimize distortions. We present experiments based on both simulation and a
real hardware optical system, from which the feasibility of the proposed
optical attack is demonstrated. It is also verified that the proposed attack is
completely different from common optical-domain distortions such as spherical
aberration, defocus, and astigmatism in terms of both perturbation patterns and
classification results.
Related papers
- Harnessing Optical Imaging Limit through Atmospheric Scattering Media [5.435475238868005]
We introduce a comprehensive model that incorporates contributions from target characteristics, atmospheric effects, imaging system, digital processing, and visual perception.
The model allows to reevaluate the effectiveness of conventional imaging recording, processing, and perception.
An immediate application of the study is the extension of the image range by an amount of 1.2 times with noise reduction via multi-frame averaging.
arXiv Detail & Related papers (2024-04-23T14:31:44Z) - NeISF: Neural Incident Stokes Field for Geometry and Material Estimation [50.588983686271284]
Multi-view inverse rendering is the problem of estimating the scene parameters such as shapes, materials, or illuminations from a sequence of images captured under different viewpoints.
We propose Neural Incident Stokes Fields (NeISF), a multi-view inverse framework that reduces ambiguities using polarization cues.
arXiv Detail & Related papers (2023-11-22T06:28:30Z) - Computational Optics for Mobile Terminals in Mass Production [17.413494778377565]
We construct the perturbed lens system model to illustrate the relationship between the system parameters and the deviated frequency response measured from photographs.
An optimization framework is proposed based on this model to build proxy cameras from the machining samples' SFRs.
Engaging with the proxy cameras, we synthetic data pairs, which encode the optical aberrations and the random manufacturing biases, for training the aberration-based algorithms.
arXiv Detail & Related papers (2023-05-10T04:17:33Z) - Optical Aberration Correction in Postprocessing using Imaging Simulation [17.331939025195478]
The popularity of mobile photography continues to grow.
Recent cameras have shifted some of these correction tasks from optical design to postprocessing systems.
We propose a practical method for recovering the degradation caused by optical aberrations.
arXiv Detail & Related papers (2023-05-10T03:20:39Z) - Neural Invertible Variable-degree Optical Aberrations Correction [6.6855248718044225]
We propose a novel aberration correction method with an invertible architecture by leveraging its information-lossless property.
Within the architecture, we develop conditional invertible blocks to allow the processing of aberrations with variable degrees.
Our method is evaluated on both a synthetic dataset from physics-based imaging simulation and a real captured dataset.
arXiv Detail & Related papers (2023-04-12T01:56:42Z) - Universal and Flexible Optical Aberration Correction Using Deep-Prior
Based Deconvolution [51.274657266928315]
We propose a PSF aware plug-and-play deep network, which takes the aberrant image and PSF map as input and produces the latent high quality version via incorporating lens-specific deep priors.
Specifically, we pre-train a base model from a set of diverse lenses and then adapt it to a given lens by quickly refining the parameters.
arXiv Detail & Related papers (2021-04-07T12:00:38Z) - Optical Flow Estimation from a Single Motion-blurred Image [66.2061278123057]
Motion blur in an image may have practical interests in fundamental computer vision problems.
We propose a novel framework to estimate optical flow from a single motion-blurred image in an end-to-end manner.
arXiv Detail & Related papers (2021-03-04T12:45:18Z) - Uncalibrated Neural Inverse Rendering for Photometric Stereo of General
Surfaces [103.08512487830669]
This paper presents an uncalibrated deep neural network framework for the photometric stereo problem.
Existing neural network-based methods either require exact light directions or ground-truth surface normals of the object or both.
We propose an uncalibrated neural inverse rendering approach to this problem.
arXiv Detail & Related papers (2020-12-12T10:33:08Z) - SIR: Self-supervised Image Rectification via Seeing the Same Scene from
Multiple Different Lenses [82.56853587380168]
We propose a novel self-supervised image rectification (SIR) method based on an important insight that the rectified results of distorted images of the same scene from different lens should be the same.
We leverage a differentiable warping module to generate the rectified images and re-distorted images from the distortion parameters.
Our method achieves comparable or even better performance than the supervised baseline method and representative state-of-the-art methods.
arXiv Detail & Related papers (2020-11-30T08:23:25Z) - Differentiable model-based adaptive optics with transmitted and
reflected light [0.0]
We show that combining model-based adaptive optics with the optimization techniques of machine learning frameworks can find aberration corrections with a small number of measurements.
Focusing in transmission can be achieved based only on reflected light, compatible with an epidetection imaging configuration.
arXiv Detail & Related papers (2020-07-27T09:39:19Z) - Deep Bilateral Retinex for Low-Light Image Enhancement [96.15991198417552]
Low-light images suffer from poor visibility caused by low contrast, color distortion and measurement noise.
This paper proposes a deep learning method for low-light image enhancement with a particular focus on handling the measurement noise.
The proposed method is very competitive to the state-of-the-art methods, and has significant advantage over others when processing images captured in extremely low lighting conditions.
arXiv Detail & Related papers (2020-07-04T06:26:44Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.