Sorry, you need to enable JavaScript to visit this website.

Multimedia security and content protection

On the Transferability of Adversarial Examples Against CNN-Based Image Forensics


Recent studies have shown that Convolutional Neural Networks (CNN) are relatively easy to attack through the generation of so-called adversarial examples. Such vulnerability also affects CNN-based image forensic tools. Research in deep learning has shown that adversarial examples exhibit a certain degree of transferability, i.e., they maintain part of their effectiveness even against CNN models other than the one targeted by the attack. This is a very strong property undermining the usability of CNN’s in security-oriented applications.

Paper Details

Authors:
Mauro Barni, Kassem Kallas, Ehsan Nowroozi, Benedetta Tondi
Submitted On:
30 January 2020 - 12:18pm
Short Link:
Type:
Event:
Presenter's Name:
Document Year:
Cite

Document Files

ICASSP 2019.pdf

(93)

Subscribe

[1] Mauro Barni, Kassem Kallas, Ehsan Nowroozi, Benedetta Tondi, "On the Transferability of Adversarial Examples Against CNN-Based Image Forensics", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/4969. Accessed: Aug. 08, 2020.
@article{4969-20,
url = {http://sigport.org/4969},
author = {Mauro Barni; Kassem Kallas; Ehsan Nowroozi; Benedetta Tondi },
publisher = {IEEE SigPort},
title = {On the Transferability of Adversarial Examples Against CNN-Based Image Forensics},
year = {2020} }
TY - EJOUR
T1 - On the Transferability of Adversarial Examples Against CNN-Based Image Forensics
AU - Mauro Barni; Kassem Kallas; Ehsan Nowroozi; Benedetta Tondi
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/4969
ER -
Mauro Barni, Kassem Kallas, Ehsan Nowroozi, Benedetta Tondi. (2020). On the Transferability of Adversarial Examples Against CNN-Based Image Forensics. IEEE SigPort. http://sigport.org/4969
Mauro Barni, Kassem Kallas, Ehsan Nowroozi, Benedetta Tondi, 2020. On the Transferability of Adversarial Examples Against CNN-Based Image Forensics. Available at: http://sigport.org/4969.
Mauro Barni, Kassem Kallas, Ehsan Nowroozi, Benedetta Tondi. (2020). "On the Transferability of Adversarial Examples Against CNN-Based Image Forensics." Web.
1. Mauro Barni, Kassem Kallas, Ehsan Nowroozi, Benedetta Tondi. On the Transferability of Adversarial Examples Against CNN-Based Image Forensics [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/4969

Effectiveness of random deep feature selection for securing image manipulation detectors against adversarial examples


We investigate if the random feature selection approach proposed in [1] to improve the robustness of forensic detectors to targeted attacks, can be extended to detectors based on deep learning features. In particular, we study the transferability of adversarial examples targeting an original CNN image manipulation detector to other detectors (a fully connected neural network and a linear SVM) that rely on a random subset of the features extracted from the flatten layer of the original network.

Paper Details

Authors:
Mauro Barni, Ehsan Nowroozi, Benedetta Tondi, Bowen Zhang
Submitted On:
30 January 2020 - 12:06pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICASSP20-final..pdf

(67)

Subscribe

[1] Mauro Barni, Ehsan Nowroozi, Benedetta Tondi, Bowen Zhang, "Effectiveness of random deep feature selection for securing image manipulation detectors against adversarial examples", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/4968. Accessed: Aug. 08, 2020.
@article{4968-20,
url = {http://sigport.org/4968},
author = {Mauro Barni; Ehsan Nowroozi; Benedetta Tondi; Bowen Zhang },
publisher = {IEEE SigPort},
title = {Effectiveness of random deep feature selection for securing image manipulation detectors against adversarial examples},
year = {2020} }
TY - EJOUR
T1 - Effectiveness of random deep feature selection for securing image manipulation detectors against adversarial examples
AU - Mauro Barni; Ehsan Nowroozi; Benedetta Tondi; Bowen Zhang
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/4968
ER -
Mauro Barni, Ehsan Nowroozi, Benedetta Tondi, Bowen Zhang. (2020). Effectiveness of random deep feature selection for securing image manipulation detectors against adversarial examples. IEEE SigPort. http://sigport.org/4968
Mauro Barni, Ehsan Nowroozi, Benedetta Tondi, Bowen Zhang, 2020. Effectiveness of random deep feature selection for securing image manipulation detectors against adversarial examples. Available at: http://sigport.org/4968.
Mauro Barni, Ehsan Nowroozi, Benedetta Tondi, Bowen Zhang. (2020). "Effectiveness of random deep feature selection for securing image manipulation detectors against adversarial examples." Web.
1. Mauro Barni, Ehsan Nowroozi, Benedetta Tondi, Bowen Zhang. Effectiveness of random deep feature selection for securing image manipulation detectors against adversarial examples [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/4968

Effectiveness of Random Deep Feature Selection for securing image manipulation detectors against adversarial examples


We investigate if the random feature selection approach proposed in [1] to improve the robustness of forensic detectors to targeted attacks, can be extended to detectors based on deep learning features. In particular, we study the transferability of adversarial examples targeting an original CNN image manipulation detector to other detectors (a fully connected neural network and a linear SVM) that rely on a random subset of the features extracted from the flatten layer of the original network.

Paper Details

Authors:
Mauro Barni, Ehsan Nowroozi, Benedetta Tondi, Bowen Zhang
Submitted On:
30 January 2020 - 12:03pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICASSP20-final..pdf

(45)

Subscribe

[1] Mauro Barni, Ehsan Nowroozi, Benedetta Tondi, Bowen Zhang, "Effectiveness of Random Deep Feature Selection for securing image manipulation detectors against adversarial examples", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/4967. Accessed: Aug. 08, 2020.
@article{4967-20,
url = {http://sigport.org/4967},
author = {Mauro Barni; Ehsan Nowroozi; Benedetta Tondi; Bowen Zhang },
publisher = {IEEE SigPort},
title = {Effectiveness of Random Deep Feature Selection for securing image manipulation detectors against adversarial examples},
year = {2020} }
TY - EJOUR
T1 - Effectiveness of Random Deep Feature Selection for securing image manipulation detectors against adversarial examples
AU - Mauro Barni; Ehsan Nowroozi; Benedetta Tondi; Bowen Zhang
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/4967
ER -
Mauro Barni, Ehsan Nowroozi, Benedetta Tondi, Bowen Zhang. (2020). Effectiveness of Random Deep Feature Selection for securing image manipulation detectors against adversarial examples. IEEE SigPort. http://sigport.org/4967
Mauro Barni, Ehsan Nowroozi, Benedetta Tondi, Bowen Zhang, 2020. Effectiveness of Random Deep Feature Selection for securing image manipulation detectors against adversarial examples. Available at: http://sigport.org/4967.
Mauro Barni, Ehsan Nowroozi, Benedetta Tondi, Bowen Zhang. (2020). "Effectiveness of Random Deep Feature Selection for securing image manipulation detectors against adversarial examples." Web.
1. Mauro Barni, Ehsan Nowroozi, Benedetta Tondi, Bowen Zhang. Effectiveness of Random Deep Feature Selection for securing image manipulation detectors against adversarial examples [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/4967

AN IMAGE IDENTIFICATION SCHEME OF ENCRYPTED JPEG IMAGES FOR PRIVACY PRESERVING PHOTO SHARING SERVICES

Paper Details

Authors:
Kenta Iida, Hitoshi Kiya
Submitted On:
29 September 2019 - 5:53am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICIP2019poster_KIida_final.pdf

(53)

Subscribe

[1] Kenta Iida, Hitoshi Kiya, "AN IMAGE IDENTIFICATION SCHEME OF ENCRYPTED JPEG IMAGES FOR PRIVACY PRESERVING PHOTO SHARING SERVICES", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4811. Accessed: Aug. 08, 2020.
@article{4811-19,
url = {http://sigport.org/4811},
author = {Kenta Iida; Hitoshi Kiya },
publisher = {IEEE SigPort},
title = {AN IMAGE IDENTIFICATION SCHEME OF ENCRYPTED JPEG IMAGES FOR PRIVACY PRESERVING PHOTO SHARING SERVICES},
year = {2019} }
TY - EJOUR
T1 - AN IMAGE IDENTIFICATION SCHEME OF ENCRYPTED JPEG IMAGES FOR PRIVACY PRESERVING PHOTO SHARING SERVICES
AU - Kenta Iida; Hitoshi Kiya
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4811
ER -
Kenta Iida, Hitoshi Kiya. (2019). AN IMAGE IDENTIFICATION SCHEME OF ENCRYPTED JPEG IMAGES FOR PRIVACY PRESERVING PHOTO SHARING SERVICES. IEEE SigPort. http://sigport.org/4811
Kenta Iida, Hitoshi Kiya, 2019. AN IMAGE IDENTIFICATION SCHEME OF ENCRYPTED JPEG IMAGES FOR PRIVACY PRESERVING PHOTO SHARING SERVICES. Available at: http://sigport.org/4811.
Kenta Iida, Hitoshi Kiya. (2019). "AN IMAGE IDENTIFICATION SCHEME OF ENCRYPTED JPEG IMAGES FOR PRIVACY PRESERVING PHOTO SHARING SERVICES." Web.
1. Kenta Iida, Hitoshi Kiya. AN IMAGE IDENTIFICATION SCHEME OF ENCRYPTED JPEG IMAGES FOR PRIVACY PRESERVING PHOTO SHARING SERVICES [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4811

Image Analysis and Processing in the Encrypted Domain


In this research project, we are interested by finding solutions to the problem of image analysis and processing in the encrypted domain. For security reasons, more and more digital data are transferred or stored in the encrypted domain. However, during the transmission or the archiving of encrypted images, it is often necessary to analyze or process them, without knowing the original content or the secret key used during the encryption phase. We propose to work on this problem, by associating theoretical aspects with numerous applications.

Paper Details

Authors:
Submitted On:
20 September 2019 - 12:16pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

20190912_Poster_3MT_ICIP2019_PPuteaux.pdf

(78)

Subscribe

[1] , "Image Analysis and Processing in the Encrypted Domain", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4792. Accessed: Aug. 08, 2020.
@article{4792-19,
url = {http://sigport.org/4792},
author = { },
publisher = {IEEE SigPort},
title = {Image Analysis and Processing in the Encrypted Domain},
year = {2019} }
TY - EJOUR
T1 - Image Analysis and Processing in the Encrypted Domain
AU -
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4792
ER -
. (2019). Image Analysis and Processing in the Encrypted Domain. IEEE SigPort. http://sigport.org/4792
, 2019. Image Analysis and Processing in the Encrypted Domain. Available at: http://sigport.org/4792.
. (2019). "Image Analysis and Processing in the Encrypted Domain." Web.
1. . Image Analysis and Processing in the Encrypted Domain [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4792

Privacy Protection for Social Media based on a Hierarchical Secret Image Sharing Scheme


Social network development raises many issues relating to privacy protection for images. In particular, multi-party privacy protection conflicts can take place when an image is published by only one of its owners. Indeed, privacy settings applied to this image are those of its owner and people on the image are not involved in the process. In this paper, we propose a new hierarchical secret image sharing scheme for social networks in order to answer this problem.

Paper Details

Authors:
Submitted On:
20 September 2019 - 11:46am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

20190920_ICIP2019_SBeugnon_PPuteaux_WPuech.pdf

(67)

Subscribe

[1] , "Privacy Protection for Social Media based on a Hierarchical Secret Image Sharing Scheme", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4790. Accessed: Aug. 08, 2020.
@article{4790-19,
url = {http://sigport.org/4790},
author = { },
publisher = {IEEE SigPort},
title = {Privacy Protection for Social Media based on a Hierarchical Secret Image Sharing Scheme},
year = {2019} }
TY - EJOUR
T1 - Privacy Protection for Social Media based on a Hierarchical Secret Image Sharing Scheme
AU -
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4790
ER -
. (2019). Privacy Protection for Social Media based on a Hierarchical Secret Image Sharing Scheme. IEEE SigPort. http://sigport.org/4790
, 2019. Privacy Protection for Social Media based on a Hierarchical Secret Image Sharing Scheme. Available at: http://sigport.org/4790.
. (2019). "Privacy Protection for Social Media based on a Hierarchical Secret Image Sharing Scheme." Web.
1. . Privacy Protection for Social Media based on a Hierarchical Secret Image Sharing Scheme [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4790