Drexel University - Comprehensive, integrated academics enhanced by co-operative education, technology, and research opportunities. | Drexel University
Drexel University
Search events. View events.

All Categories

Click for help in using calendar displays. Print the contents of the current screen.
Display Format: 
Event Details
Notify me if this event changes.Add this event to my personal calendar.
Go Back
ECE Seminar Series: Xinwei Zhao
Start Date: 1/15/2019Start Time: 4:00 PM
End Date: 1/15/2019End Time: 5:00 PM

Event Description
Title: Using Deep Learning Techniques for Image Source Falsification

Abstract:
Deep learning techniques have become popular for performing camera model identification. To expose weaknesses in these methods, we propose a new anti-forensic framework that utilizes a generative adversarial network (GAN) to falsify an image's source camera model. Our proposed attack uses the generator trained in the GAN to produce an image that can fool a CNN-based camera model identification classifier. Moreover, our proposed attack will only introduce a minimal amount of distortion to the falsified image that is not perceptible to human eyes. By conducting experiments on a large amount of data, we show that the proposed attack can successfully fool a state-of-art camera model identification CNN classifier with 98% probability and maintain high image quality.

Link of the paper: https://ieeexplore.ieee.org/document/8451503
Contact Information:
Name: Sean Clark
Phone: 2158956658
Email: swc37@drexel.edu
Location:
Bossone 302
Audience:
  • Everyone

  • Display Month:

    Advanced Search (New Search)
    Date Range:
    Time Range:
    Category(s):
    Audience: 

    Special Features: 

    Keyword(s):
    Submit
    Select item(s) to Search
    Select item(s) to Search
    Select item(s) to Search
    Select item(s) to Search