DeepSonar: Towards effective and robust detection of AI-synthesized fake voices

With the recent advances in voice synthesis, AI-synthesized fake voices are indistinguishable to human ears and widely are applied to produce realistic and natural DeepFakes, exhibiting real threats to our society. However, effective and robust detectors for synthesized fake voices are still in thei...

Full description

Saved in:
Bibliographic Details
Main Authors: WANG, Run, JUEFEI-XU, Felix, HUANG, Yihao, GUO, Qing, XIE, Xiaofei, MA, Lei, LIU, Yang
Format: text
Language:English
Published: Institutional Knowledge at Singapore Management University 2020
Subjects:
Online Access:https://ink.library.smu.edu.sg/sis_research/7082
https://ink.library.smu.edu.sg/context/sis_research/article/8085/viewcontent/3394171.3413716.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-8085
record_format dspace
spelling sg-smu-ink.sis_research-80852022-04-07T08:04:05Z DeepSonar: Towards effective and robust detection of AI-synthesized fake voices WANG, Run JUEFEI-XU, Felix HUANG, Yihao GUO, Qing XIE, Xiaofei MA, Lei LIU, Yang With the recent advances in voice synthesis, AI-synthesized fake voices are indistinguishable to human ears and widely are applied to produce realistic and natural DeepFakes, exhibiting real threats to our society. However, effective and robust detectors for synthesized fake voices are still in their infancy and are not ready to fully tackle this emerging threat. In this paper, we devise a novel approach, named DeepSonar, based on monitoring neuron behaviors of speaker recognition (SR) system, i.e., a deep neural network (DNN), to discern AI-synthesized fake voices. Layer-wise neuron behaviors provide an important insight to meticulously catch the differences among inputs, which are widely employed for building safety, robust, and interpretable DNNs. In this work, we leverage the power of layer-wise neuron activation patterns with a conjecture that they can capture the subtle differences between real and AI-synthesized fake voices, in providing a cleaner signal to classifiers than raw inputs. Experiments are conducted on three datasets (including commercial products from Google, Baidu, etc) containing both English and Chinese languages to corroborate the high detection rates (98.1% average accuracy) and low false alarm rates (about 2% error rate) of DeepSonar in discerning fake voices. Furthermore, extensive experimental results also demonstrate its robustness against manipulation attacks (e.g., voice conversion and additive real-world noises). Our work further poses a new insight into adopting neuron behaviors for effective and robust AI aided multimedia fakes forensics as an inside-out approach instead of being motivated and swayed by various artifacts introduced in synthesizing fakes. 2020-10-01T07:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/7082 info:doi/10.1145/3394171.3413716 https://ink.library.smu.edu.sg/context/sis_research/article/8085/viewcontent/3394171.3413716.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 DeepFake fake voice neuron behavior OS and Networks Software Engineering
institution Singapore Management University
building SMU Libraries
continent Asia
country Singapore
Singapore
content_provider SMU Libraries
collection InK@SMU
language English
topic DeepFake
fake voice
neuron behavior
OS and Networks
Software Engineering
spellingShingle DeepFake
fake voice
neuron behavior
OS and Networks
Software Engineering
WANG, Run
JUEFEI-XU, Felix
HUANG, Yihao
GUO, Qing
XIE, Xiaofei
MA, Lei
LIU, Yang
DeepSonar: Towards effective and robust detection of AI-synthesized fake voices
description With the recent advances in voice synthesis, AI-synthesized fake voices are indistinguishable to human ears and widely are applied to produce realistic and natural DeepFakes, exhibiting real threats to our society. However, effective and robust detectors for synthesized fake voices are still in their infancy and are not ready to fully tackle this emerging threat. In this paper, we devise a novel approach, named DeepSonar, based on monitoring neuron behaviors of speaker recognition (SR) system, i.e., a deep neural network (DNN), to discern AI-synthesized fake voices. Layer-wise neuron behaviors provide an important insight to meticulously catch the differences among inputs, which are widely employed for building safety, robust, and interpretable DNNs. In this work, we leverage the power of layer-wise neuron activation patterns with a conjecture that they can capture the subtle differences between real and AI-synthesized fake voices, in providing a cleaner signal to classifiers than raw inputs. Experiments are conducted on three datasets (including commercial products from Google, Baidu, etc) containing both English and Chinese languages to corroborate the high detection rates (98.1% average accuracy) and low false alarm rates (about 2% error rate) of DeepSonar in discerning fake voices. Furthermore, extensive experimental results also demonstrate its robustness against manipulation attacks (e.g., voice conversion and additive real-world noises). Our work further poses a new insight into adopting neuron behaviors for effective and robust AI aided multimedia fakes forensics as an inside-out approach instead of being motivated and swayed by various artifacts introduced in synthesizing fakes.
format text
author WANG, Run
JUEFEI-XU, Felix
HUANG, Yihao
GUO, Qing
XIE, Xiaofei
MA, Lei
LIU, Yang
author_facet WANG, Run
JUEFEI-XU, Felix
HUANG, Yihao
GUO, Qing
XIE, Xiaofei
MA, Lei
LIU, Yang
author_sort WANG, Run
title DeepSonar: Towards effective and robust detection of AI-synthesized fake voices
title_short DeepSonar: Towards effective and robust detection of AI-synthesized fake voices
title_full DeepSonar: Towards effective and robust detection of AI-synthesized fake voices
title_fullStr DeepSonar: Towards effective and robust detection of AI-synthesized fake voices
title_full_unstemmed DeepSonar: Towards effective and robust detection of AI-synthesized fake voices
title_sort deepsonar: towards effective and robust detection of ai-synthesized fake voices
publisher Institutional Knowledge at Singapore Management University
publishDate 2020
url https://ink.library.smu.edu.sg/sis_research/7082
https://ink.library.smu.edu.sg/context/sis_research/article/8085/viewcontent/3394171.3413716.pdf
_version_ 1770576208596041728