FakeSpotter: A simple yet robust baseline for spotting AI-synthesized fake faces

In recent years, generative adversarial networks (GANs) and its variants have achieved unprecedented success in image synthesis. They are widely adopted in synthesizing facial images which brings potential security concerns to humans as the fakes spread and fuel the misinformation. However, robust d...

Full description

Saved in:
Bibliographic Details
Main Authors: WANG, Run, JUEFEI-XU, Felix, MA, Lei, XIE, Xiaofei, HUANG, Yihao, WANG, Jian, LIU, Yang
Format: text
Language:English
Published: Institutional Knowledge at Singapore Management University 2021
Subjects:
Online Access:https://ink.library.smu.edu.sg/sis_research/7106
https://ink.library.smu.edu.sg/context/sis_research/article/8109/viewcontent/3491440.3491916.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Singapore Management University
Language: English
id sg-smu-ink.sis_research-8109
record_format dspace
spelling sg-smu-ink.sis_research-81092022-04-14T11:51:59Z FakeSpotter: A simple yet robust baseline for spotting AI-synthesized fake faces WANG, Run JUEFEI-XU, Felix MA, Lei XIE, Xiaofei HUANG, Yihao WANG, Jian LIU, Yang In recent years, generative adversarial networks (GANs) and its variants have achieved unprecedented success in image synthesis. They are widely adopted in synthesizing facial images which brings potential security concerns to humans as the fakes spread and fuel the misinformation. However, robust detectors of these AI-synthesized fake faces are still in their infancy and are not ready to fully tackle this emerging challenge. In this work, we propose a novel approach, named FakeSpotter, based on monitoring neuron behaviors to spot AIsynthesized fake faces. The studies on neuron coverage and interactions have successfully shown that they can be served as testing criteria for deep learning systems, especially under the settings of being exposed to adversarial attacks. Here, we conjecture that monitoring neuron behavior can also serve as an asset in detecting fake faces since layer-bylayer neuron activation patterns may capture more subtle features that are important for the fake detector. Experimental results on detecting four types of fake faces synthesized with the state-of-the-art GANs and evading four perturbation attacks show the effectiveness and robustness of our approach. 2021-01-01T08:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/7106 info:doi/10.5555/3491440.3491916 https://ink.library.smu.edu.sg/context/sis_research/article/8109/viewcontent/3491440.3491916.pdf http://creativecommons.org/licenses/by-nc-nd/4.0/ Research Collection School Of Computing and Information Systems eng Institutional Knowledge at Singapore Management University Artificial Intelligence and Robotics Software Engineering
institution Singapore Management University
building SMU Libraries
continent Asia
country Singapore
Singapore
content_provider SMU Libraries
collection InK@SMU
language English
topic Artificial Intelligence and Robotics
Software Engineering
spellingShingle Artificial Intelligence and Robotics
Software Engineering
WANG, Run
JUEFEI-XU, Felix
MA, Lei
XIE, Xiaofei
HUANG, Yihao
WANG, Jian
LIU, Yang
FakeSpotter: A simple yet robust baseline for spotting AI-synthesized fake faces
description In recent years, generative adversarial networks (GANs) and its variants have achieved unprecedented success in image synthesis. They are widely adopted in synthesizing facial images which brings potential security concerns to humans as the fakes spread and fuel the misinformation. However, robust detectors of these AI-synthesized fake faces are still in their infancy and are not ready to fully tackle this emerging challenge. In this work, we propose a novel approach, named FakeSpotter, based on monitoring neuron behaviors to spot AIsynthesized fake faces. The studies on neuron coverage and interactions have successfully shown that they can be served as testing criteria for deep learning systems, especially under the settings of being exposed to adversarial attacks. Here, we conjecture that monitoring neuron behavior can also serve as an asset in detecting fake faces since layer-bylayer neuron activation patterns may capture more subtle features that are important for the fake detector. Experimental results on detecting four types of fake faces synthesized with the state-of-the-art GANs and evading four perturbation attacks show the effectiveness and robustness of our approach.
format text
author WANG, Run
JUEFEI-XU, Felix
MA, Lei
XIE, Xiaofei
HUANG, Yihao
WANG, Jian
LIU, Yang
author_facet WANG, Run
JUEFEI-XU, Felix
MA, Lei
XIE, Xiaofei
HUANG, Yihao
WANG, Jian
LIU, Yang
author_sort WANG, Run
title FakeSpotter: A simple yet robust baseline for spotting AI-synthesized fake faces
title_short FakeSpotter: A simple yet robust baseline for spotting AI-synthesized fake faces
title_full FakeSpotter: A simple yet robust baseline for spotting AI-synthesized fake faces
title_fullStr FakeSpotter: A simple yet robust baseline for spotting AI-synthesized fake faces
title_full_unstemmed FakeSpotter: A simple yet robust baseline for spotting AI-synthesized fake faces
title_sort fakespotter: a simple yet robust baseline for spotting ai-synthesized fake faces
publisher Institutional Knowledge at Singapore Management University
publishDate 2021
url https://ink.library.smu.edu.sg/sis_research/7106
https://ink.library.smu.edu.sg/context/sis_research/article/8109/viewcontent/3491440.3491916.pdf
_version_ 1770576213579923456