Improving the Authentication with Built-in Camera Protocol Using Built-in Motion Sensors: A Deep Learning Solution

  title={Improving the Authentication with Built-in Camera Protocol Using Built-in Motion Sensors: A Deep Learning Solution},
  author={Cezara Benegui and Radu Tudor Ionescu},
In this paper, we propose an enhanced version of the Authentication with Built-in Camera (ABC) protocol by employing a deep learning solution based on built-in motion sensors. The standard ABC protocol identifies mobile devices based on the photo-response non-uniformity (PRNU) of the camera sensor, while also considering QR-code-based meta-information. During registration, users are required to capture photos using their smartphone camera. The photos are sent to a server that computes the… Expand

Figures and Tables from this paper


A breach into the Authentication with Built-in Camera (ABC) Protocol
In this paper, we propose a simple and effective attack on the recently introduced Smartphone Authentication with Built-in Camera Protocol, called ABC. The ABC protocol uses the photo-responseExpand
ABC: Enabling Smartphone Authentication with Built-in Camera
The first to observe that one image alone can uniquely identify a smartphone due to the unique PRNU of a smartphone image sensor, makes the use ofPRNU practical for smartphone authentication practical. Expand
Digital camera identification using PRNU: A feature based approach
The proposed feature based approach of PRNU is demonstrated to be capable of identifying the source camera of the given image with good accuracy and showed that the proposed technique remains robust even if the images are subjected to simple manipulations or geometric variations. Expand
Robust smartphone fingerprint by mixing device sensors features for mobile strong authentication
The objective is to introduce a novel methodology to obtain a robust smartphone fingerprint by opportunely combining different intrinsic characteristics of each sensor, based on the individuation and definition of a set of distinctive features for each sensor. Expand
Defending Against Fingerprint-Copy Attack in Sensor-Based Camera Identification
The conclusion that can be made from this study is that planting a sensor fingerprint in an image without leaving a trace is significantly more difficult than previously thought. Expand
Enhancing Source Camera Identification Performance With a Camera Reference Phase Sensor Pattern Noise
Theoretical analysis shows that the proposed CI method can remove the interference and raise the CCN value of a positive sample and thus achieve greater CI performance, and CCN values of the negative sample class with the proposed method follow the normal distribution N (0,1) and the false positive rate can be calculated. Expand
Hold and Sign: A Novel Behavioral Biometrics for Smartphone User Authentication
A new, bi-modal behavioral biometric solution for user authentication that takes into account micro-movements of a phone and movements of the user's finger during writing or signing on the touchscreen. Expand
Digital Camera Identification from Images - Estimating False Acceptance Probability
  • M. Goljan
  • Computer Science, Mathematics
  • IWDW
  • 2008
The state-of-the-art identification method using photo-response non-uniformity noise present in output signals of CCD and CMOS sensors to uniquely identify the source digital camera that took the image is reviewed and a novel approach is based on cross-correlation analysis and peak-to-cor correlation-energy ratio. Expand
Context-Aware Implicit Authentication of Smartphone Users Based on Multi-Sensor Behavior
A context-aware implicit authentication is proposed, which is a scheme to improve the robustness of authentication by introducing context awareness module and can effectively improve the reliability and practicability of implicit authentication. Expand
Convolutional Neural Networks for User Identification Based on Motion Sensors Represented as Images
This paper transforms the discrete 3-axis signals from the motion sensors into a gray-scale image representation which is provided as input to a convolutional neural network (CNN) that is pre-trained for multi-class user classification. Expand