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

Multimedia Forensics

Information Theoretical Limit of Operation Forensics


Abstract—While more and more forensic techniques have been proposed to detect the processing history of multimedia content, one starts to wonder if there exists a fundamental limit on the capability of forensics. In other words, besides keeping on searching what investigators can do, it is also important to find out the limit of their capability and what they cannot do. In this work, we explore the fundamental limit of operation forensics by proposing an information theoretical framework.

Paper Details

Authors:
Matthew C. Stamm
Submitted On:
23 February 2016 - 1:44pm
Short Link:
Type:

Document Files

double_RQ.pdf

(778)

Subscribe

[1] Matthew C. Stamm, "Information Theoretical Limit of Operation Forensics", IEEE SigPort, 2015. [Online]. Available: http://sigport.org/147. Accessed: Aug. 12, 2020.
@article{147-15,
url = {http://sigport.org/147},
author = {Matthew C. Stamm },
publisher = {IEEE SigPort},
title = {Information Theoretical Limit of Operation Forensics},
year = {2015} }
TY - EJOUR
T1 - Information Theoretical Limit of Operation Forensics
AU - Matthew C. Stamm
PY - 2015
PB - IEEE SigPort
UR - http://sigport.org/147
ER -
Matthew C. Stamm. (2015). Information Theoretical Limit of Operation Forensics. IEEE SigPort. http://sigport.org/147
Matthew C. Stamm, 2015. Information Theoretical Limit of Operation Forensics. Available at: http://sigport.org/147.
Matthew C. Stamm. (2015). "Information Theoretical Limit of Operation Forensics." Web.
1. Matthew C. Stamm. Information Theoretical Limit of Operation Forensics [Internet]. IEEE SigPort; 2015. Available from : http://sigport.org/147

Compressive Sensing Forensics


Abstract—Identifying a signal’s origin and how it was acquired is an important forensic problem. While forensic techniques currently exist to determine a signal’s acquisition history, these techniques do not account for the possibility that a signal could be compressively sensed. This is an important problem since compressive sensing techniques have seen increased popularity in recent years. In this paper, we propose a set of forensic techniques to identify signals acquired by compressive sensing. We do this by first identifying the fingerprints left in a signal by compressive sensing.

Paper Details

Authors:
Matthew C. Stamm
Submitted On:
23 February 2016 - 1:43pm
Short Link:
Type:

Document Files

double_AQ.pdf

(650)

Subscribe

[1] Matthew C. Stamm, "Compressive Sensing Forensics", IEEE SigPort, 2015. [Online]. Available: http://sigport.org/146. Accessed: Aug. 12, 2020.
@article{146-15,
url = {http://sigport.org/146},
author = {Matthew C. Stamm },
publisher = {IEEE SigPort},
title = {Compressive Sensing Forensics},
year = {2015} }
TY - EJOUR
T1 - Compressive Sensing Forensics
AU - Matthew C. Stamm
PY - 2015
PB - IEEE SigPort
UR - http://sigport.org/146
ER -
Matthew C. Stamm. (2015). Compressive Sensing Forensics. IEEE SigPort. http://sigport.org/146
Matthew C. Stamm, 2015. Compressive Sensing Forensics. Available at: http://sigport.org/146.
Matthew C. Stamm. (2015). "Compressive Sensing Forensics." Web.
1. Matthew C. Stamm. Compressive Sensing Forensics [Internet]. IEEE SigPort; 2015. Available from : http://sigport.org/146

Learning to Fool the Speaker Recognition (poster)


Due to the widespread deployment of fingerprint/face/speaker recognition systems, attacking deep learning based biometric systems has drawn more and more attention. Previous research mainly studied the attack to the vision-based system, such as fingerprint and face recognition. While the attack for speaker recognition has not been investigated yet, although it has been widely used in our daily life.

Paper Details

Authors:
Submitted On:
9 June 2020 - 11:26am
Short Link:
Type:
Event:
Presenter's Name:
Document Year:
Cite

Document Files

preid_453146_learning_to_fool_the_speaker_recognition_ICASSP2020.pdf

(38)

Subscribe

[1] , "Learning to Fool the Speaker Recognition (poster)", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5462. Accessed: Aug. 12, 2020.
@article{5462-20,
url = {http://sigport.org/5462},
author = { },
publisher = {IEEE SigPort},
title = {Learning to Fool the Speaker Recognition (poster)},
year = {2020} }
TY - EJOUR
T1 - Learning to Fool the Speaker Recognition (poster)
AU -
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5462
ER -
. (2020). Learning to Fool the Speaker Recognition (poster). IEEE SigPort. http://sigport.org/5462
, 2020. Learning to Fool the Speaker Recognition (poster). Available at: http://sigport.org/5462.
. (2020). "Learning to Fool the Speaker Recognition (poster)." Web.
1. . Learning to Fool the Speaker Recognition (poster) [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5462

EMET : EMBEDDINGS FROM MULTILINGUAL- ENCODER TRANSFORMER FOR FAKE NEWS DETECTION


In the last few years, social media networks have changed human life experience and behavior as it has broken down communication barriers, allowing ordinary people to actively produce multimedia content on a massive scale. On this wise, the information dissemination in social media platforms becomes increasingly common. However, misinformation is propagated with the same facility and velocity as real news, though it can result in irreversible damage to an individual or society at large.

Paper Details

Authors:
Stephane Schwarz ; Antônio Theóphilo ; Anderson Rocha
Submitted On:
20 May 2020 - 11:36am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICASSP.pdf

(25)

Subscribe

[1] Stephane Schwarz ; Antônio Theóphilo ; Anderson Rocha , "EMET : EMBEDDINGS FROM MULTILINGUAL- ENCODER TRANSFORMER FOR FAKE NEWS DETECTION", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5417. Accessed: Aug. 12, 2020.
@article{5417-20,
url = {http://sigport.org/5417},
author = {Stephane Schwarz ; Antônio Theóphilo ; Anderson Rocha },
publisher = {IEEE SigPort},
title = {EMET : EMBEDDINGS FROM MULTILINGUAL- ENCODER TRANSFORMER FOR FAKE NEWS DETECTION},
year = {2020} }
TY - EJOUR
T1 - EMET : EMBEDDINGS FROM MULTILINGUAL- ENCODER TRANSFORMER FOR FAKE NEWS DETECTION
AU - Stephane Schwarz ; Antônio Theóphilo ; Anderson Rocha
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5417
ER -
Stephane Schwarz ; Antônio Theóphilo ; Anderson Rocha . (2020). EMET : EMBEDDINGS FROM MULTILINGUAL- ENCODER TRANSFORMER FOR FAKE NEWS DETECTION. IEEE SigPort. http://sigport.org/5417
Stephane Schwarz ; Antônio Theóphilo ; Anderson Rocha , 2020. EMET : EMBEDDINGS FROM MULTILINGUAL- ENCODER TRANSFORMER FOR FAKE NEWS DETECTION. Available at: http://sigport.org/5417.
Stephane Schwarz ; Antônio Theóphilo ; Anderson Rocha . (2020). "EMET : EMBEDDINGS FROM MULTILINGUAL- ENCODER TRANSFORMER FOR FAKE NEWS DETECTION." Web.
1. Stephane Schwarz ; Antônio Theóphilo ; Anderson Rocha . EMET : EMBEDDINGS FROM MULTILINGUAL- ENCODER TRANSFORMER FOR FAKE NEWS DETECTION [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5417

Multi-Patch Aggregation Models for Resampling Detection


Images captured nowadays are of varying dimensions with smartphones and DSLR’s allowing users to choose from a list of available image resolutions. It is therefore imperative for forensic algorithms such as resampling detection to scale well for images of varying dimensions. However, in our experiments we observed that many state-of-the-art forensic algorithms are sensitive to image size and their performance quickly degenerates when operated on images of diverse dimensions despite re-training them using multiple image sizes.

Paper Details

Authors:
Mohit Lamba, Kaushik Mitra
Submitted On:
16 May 2020 - 12:48am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

Presentation Slides for the project

(24)

Keywords

Additional Categories

Subscribe

[1] Mohit Lamba, Kaushik Mitra, "Multi-Patch Aggregation Models for Resampling Detection", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5367. Accessed: Aug. 12, 2020.
@article{5367-20,
url = {http://sigport.org/5367},
author = {Mohit Lamba; Kaushik Mitra },
publisher = {IEEE SigPort},
title = {Multi-Patch Aggregation Models for Resampling Detection},
year = {2020} }
TY - EJOUR
T1 - Multi-Patch Aggregation Models for Resampling Detection
AU - Mohit Lamba; Kaushik Mitra
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5367
ER -
Mohit Lamba, Kaushik Mitra. (2020). Multi-Patch Aggregation Models for Resampling Detection. IEEE SigPort. http://sigport.org/5367
Mohit Lamba, Kaushik Mitra, 2020. Multi-Patch Aggregation Models for Resampling Detection. Available at: http://sigport.org/5367.
Mohit Lamba, Kaushik Mitra. (2020). "Multi-Patch Aggregation Models for Resampling Detection." Web.
1. Mohit Lamba, Kaushik Mitra. Multi-Patch Aggregation Models for Resampling Detection [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5367

Augmentation Data Synthesis via GANs: Boosting Latent Fingerprint Reconstruction


Latent fingerprint reconstruction is a vital preprocessing step for its identification. This task is very challenging due to not only existing complicated degradation patterns but also its scarcity of paired training data. To address these challenges, we propose a novel generative adversarial network (GAN) based data augmentation scheme to improve such reconstruction.

Paper Details

Authors:
Ying Xu, Yi Wang, Jiajun Liang, Yong Jiang
Submitted On:
15 May 2020 - 1:16am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICASSP1263.pdf

(27)

Subscribe

[1] Ying Xu, Yi Wang, Jiajun Liang, Yong Jiang, "Augmentation Data Synthesis via GANs: Boosting Latent Fingerprint Reconstruction", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5335. Accessed: Aug. 12, 2020.
@article{5335-20,
url = {http://sigport.org/5335},
author = {Ying Xu; Yi Wang; Jiajun Liang; Yong Jiang },
publisher = {IEEE SigPort},
title = {Augmentation Data Synthesis via GANs: Boosting Latent Fingerprint Reconstruction},
year = {2020} }
TY - EJOUR
T1 - Augmentation Data Synthesis via GANs: Boosting Latent Fingerprint Reconstruction
AU - Ying Xu; Yi Wang; Jiajun Liang; Yong Jiang
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5335
ER -
Ying Xu, Yi Wang, Jiajun Liang, Yong Jiang. (2020). Augmentation Data Synthesis via GANs: Boosting Latent Fingerprint Reconstruction. IEEE SigPort. http://sigport.org/5335
Ying Xu, Yi Wang, Jiajun Liang, Yong Jiang, 2020. Augmentation Data Synthesis via GANs: Boosting Latent Fingerprint Reconstruction. Available at: http://sigport.org/5335.
Ying Xu, Yi Wang, Jiajun Liang, Yong Jiang. (2020). "Augmentation Data Synthesis via GANs: Boosting Latent Fingerprint Reconstruction." Web.
1. Ying Xu, Yi Wang, Jiajun Liang, Yong Jiang. Augmentation Data Synthesis via GANs: Boosting Latent Fingerprint Reconstruction [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5335

A DENSE U-NET WITH CROSS LAYER INTERSECTION FOR DETECTION AND LOCALIZATION OF IMAGE FORGERY


In this paper, we apply cross-layer intersection mechanism to dense u-net for image forgery detection and localization. We first train DenseNet for binary classification. Spatial rich model (SRM) filters are adopted for capturing residual signals in the detected images. Then we propose a new approach to preserve complete feature maps of fully connected layer and consider them as the spatial decision information for image segmentation.

Paper Details

Authors:
Rongyu Zhang, JiangqunNi
Submitted On:
14 May 2020 - 12:34am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICASSP_2020_A DENSE_U-NET_WITH_CROSS_LAYER_INTERSECTION_FOR_DETECTION_AND_LOCALIZATION_OF_IMAGE_FORGERY.pptx

(30)

Subscribe

[1] Rongyu Zhang, JiangqunNi, "A DENSE U-NET WITH CROSS LAYER INTERSECTION FOR DETECTION AND LOCALIZATION OF IMAGE FORGERY", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5220. Accessed: Aug. 12, 2020.
@article{5220-20,
url = {http://sigport.org/5220},
author = {Rongyu Zhang; JiangqunNi },
publisher = {IEEE SigPort},
title = {A DENSE U-NET WITH CROSS LAYER INTERSECTION FOR DETECTION AND LOCALIZATION OF IMAGE FORGERY},
year = {2020} }
TY - EJOUR
T1 - A DENSE U-NET WITH CROSS LAYER INTERSECTION FOR DETECTION AND LOCALIZATION OF IMAGE FORGERY
AU - Rongyu Zhang; JiangqunNi
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5220
ER -
Rongyu Zhang, JiangqunNi. (2020). A DENSE U-NET WITH CROSS LAYER INTERSECTION FOR DETECTION AND LOCALIZATION OF IMAGE FORGERY. IEEE SigPort. http://sigport.org/5220
Rongyu Zhang, JiangqunNi, 2020. A DENSE U-NET WITH CROSS LAYER INTERSECTION FOR DETECTION AND LOCALIZATION OF IMAGE FORGERY. Available at: http://sigport.org/5220.
Rongyu Zhang, JiangqunNi. (2020). "A DENSE U-NET WITH CROSS LAYER INTERSECTION FOR DETECTION AND LOCALIZATION OF IMAGE FORGERY." Web.
1. Rongyu Zhang, JiangqunNi. A DENSE U-NET WITH CROSS LAYER INTERSECTION FOR DETECTION AND LOCALIZATION OF IMAGE FORGERY [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5220

Luminance-based Video Backdoor Attack Against Anti-spoofing Rebroadcast Detection

Paper Details

Authors:
Abhir Bhalerao, Mauro Barni, Kassem Kallas, Benedetta Tondi
Submitted On:
25 September 2019 - 3:57am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

MMSP2019.pdf

(95)

Subscribe

[1] Abhir Bhalerao, Mauro Barni, Kassem Kallas, Benedetta Tondi, "Luminance-based Video Backdoor Attack Against Anti-spoofing Rebroadcast Detection", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4839. Accessed: Aug. 12, 2020.
@article{4839-19,
url = {http://sigport.org/4839},
author = {Abhir Bhalerao; Mauro Barni; Kassem Kallas; Benedetta Tondi },
publisher = {IEEE SigPort},
title = {Luminance-based Video Backdoor Attack Against Anti-spoofing Rebroadcast Detection},
year = {2019} }
TY - EJOUR
T1 - Luminance-based Video Backdoor Attack Against Anti-spoofing Rebroadcast Detection
AU - Abhir Bhalerao; Mauro Barni; Kassem Kallas; Benedetta Tondi
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4839
ER -
Abhir Bhalerao, Mauro Barni, Kassem Kallas, Benedetta Tondi. (2019). Luminance-based Video Backdoor Attack Against Anti-spoofing Rebroadcast Detection. IEEE SigPort. http://sigport.org/4839
Abhir Bhalerao, Mauro Barni, Kassem Kallas, Benedetta Tondi, 2019. Luminance-based Video Backdoor Attack Against Anti-spoofing Rebroadcast Detection. Available at: http://sigport.org/4839.
Abhir Bhalerao, Mauro Barni, Kassem Kallas, Benedetta Tondi. (2019). "Luminance-based Video Backdoor Attack Against Anti-spoofing Rebroadcast Detection." Web.
1. Abhir Bhalerao, Mauro Barni, Kassem Kallas, Benedetta Tondi. Luminance-based Video Backdoor Attack Against Anti-spoofing Rebroadcast Detection [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4839

A new Backdoor Attack in CNNs by training set corruption without label poisoning


Backdoor attacks against CNNs represent a new threat against deep learning systems, due to the possibility of corrupting the training set so to induce an incorrect behaviour at test time. To avoid that the trainer recognises the presence of the corrupted samples, the corruption of the training set must be as stealthy as possible. Previous works have focused on the stealthiness of the perturbation injected into the training samples, however they all assume that the labels of the corrupted samples are also poisoned.

Paper Details

Authors:
Submitted On:
19 September 2019 - 9:18am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICIP2019.pdf

(81)

Subscribe

[1] , "A new Backdoor Attack in CNNs by training set corruption without label poisoning", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4732. Accessed: Aug. 12, 2020.
@article{4732-19,
url = {http://sigport.org/4732},
author = { },
publisher = {IEEE SigPort},
title = {A new Backdoor Attack in CNNs by training set corruption without label poisoning},
year = {2019} }
TY - EJOUR
T1 - A new Backdoor Attack in CNNs by training set corruption without label poisoning
AU -
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4732
ER -
. (2019). A new Backdoor Attack in CNNs by training set corruption without label poisoning. IEEE SigPort. http://sigport.org/4732
, 2019. A new Backdoor Attack in CNNs by training set corruption without label poisoning. Available at: http://sigport.org/4732.
. (2019). "A new Backdoor Attack in CNNs by training set corruption without label poisoning." Web.
1. . A new Backdoor Attack in CNNs by training set corruption without label poisoning [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4732

Sentiment Aware Fake News Detection on Online Social Networks

Paper Details

Authors:
Oluwaseun Ajao, Deepayan Bhowmik, Shahrzad Zargari
Submitted On:
19 May 2019 - 7:04pm
Short Link:
Type:
Event:
Paper Code:
Document Year:
Cite

Document Files

Poster-ICASSP2019

(128)

Subscribe

[1] Oluwaseun Ajao, Deepayan Bhowmik, Shahrzad Zargari, "Sentiment Aware Fake News Detection on Online Social Networks", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4552. Accessed: Aug. 12, 2020.
@article{4552-19,
url = {http://sigport.org/4552},
author = {Oluwaseun Ajao; Deepayan Bhowmik; Shahrzad Zargari },
publisher = {IEEE SigPort},
title = {Sentiment Aware Fake News Detection on Online Social Networks},
year = {2019} }
TY - EJOUR
T1 - Sentiment Aware Fake News Detection on Online Social Networks
AU - Oluwaseun Ajao; Deepayan Bhowmik; Shahrzad Zargari
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4552
ER -
Oluwaseun Ajao, Deepayan Bhowmik, Shahrzad Zargari. (2019). Sentiment Aware Fake News Detection on Online Social Networks. IEEE SigPort. http://sigport.org/4552
Oluwaseun Ajao, Deepayan Bhowmik, Shahrzad Zargari, 2019. Sentiment Aware Fake News Detection on Online Social Networks. Available at: http://sigport.org/4552.
Oluwaseun Ajao, Deepayan Bhowmik, Shahrzad Zargari. (2019). "Sentiment Aware Fake News Detection on Online Social Networks." Web.
1. Oluwaseun Ajao, Deepayan Bhowmik, Shahrzad Zargari. Sentiment Aware Fake News Detection on Online Social Networks [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4552

Pages