Moiré Attack (MA): A New Potential Risk of Screen Photos

by   Dantong Niu, et al.

Images, captured by a camera, play a critical role in training Deep Neural Networks (DNNs). Usually, we assume the images acquired by cameras are consistent with the ones perceived by human eyes. However, due to the different physical mechanisms between human-vision and computer-vision systems, the final perceived images could be very different in some cases, for example shooting on digital monitors. In this paper, we find a special phenomenon in digital image processing, the moiré effect, that could cause unnoticed security threats to DNNs. Based on it, we propose a Moiré Attack (MA) that generates the physical-world moiré pattern adding to the images by mimicking the shooting process of digital devices. Extensive experiments demonstrate that our proposed digital Moiré Attack (MA) is a perfect camouflage for attackers to tamper with DNNs with a high success rate (100.0% for untargeted and 97.0% for targeted attack with the noise budget ϵ=4), high transferability rate across different models, and high robustness under various defenses. Furthermore, MA owns great stealthiness because the moiré effect is unavoidable due to the camera's inner physical structure, which therefore hardly attracts the awareness of humans. Our code is available at


page 2

page 4

page 7

page 9

page 10

page 13

page 14

page 15


Imperceptible Backdoor Attack: From Input Space to Feature Representation

Backdoor attacks are rapidly emerging threats to deep neural networks (D...

Physical Adversarial Attack meets Computer Vision: A Decade Survey

Although Deep Neural Networks (DNNs) have achieved impressive results in...

Adversarial Color Film: Effective Physical-World Attack to DNNs

It is well known that the performance of deep neural networks (DNNs) is ...

Adversarial Exposure Attack on Diabetic Retinopathy Imagery

Diabetic retinopathy (DR) is a leading cause of vision loss in the world...

Aparecium: Revealing Secrets from Physical Photographs

Watermarking is a crucial tool for safeguarding copyrights and can serve...

One-bit Flip is All You Need: When Bit-flip Attack Meets Model Training

Deep neural networks (DNNs) are widely deployed on real-world devices. C...

Untargeted Backdoor Attack against Object Detection

Recent studies revealed that deep neural networks (DNNs) are exposed to ...

Please sign up or login with your details

Forgot password? Click here to reset