Video Manipulation Detection Based on Metadata Analysis Presented @ ICML 2019

David Güera (Purdue University) presents the video manipulation detection method developed in partnership with ISPL [1]. This work was accepted as contribution to the workshop “Deep Learning for Detecting AudioVisual Fakes” at ICML 2019.

[1] D. Güera, S. Baireddy, P. Bestagini, S. Tubaro, and E. J. Delp, “We Need No Pixels: Video Manipulation Detection Using Stream Descriptors,” in International Conference on Machine Learning (ICML), Synthetic Realities: Deep Learning for Detecting AudioVisual Fakes Workshop, 2019.
[Bibtex]
@inproceedings{gueera2019we,
author = {G{\"u}era, D. and Baireddy, S. and Bestagini, P. and Tubaro, S. and Delp, E. J.},
booktitle = {International Conference on Machine Learning (ICML), Synthetic Realities: Deep Learning for Detecting AudioVisual Fakes Workshop},
groups = {forensics},
title = {We Need No Pixels: Video Manipulation Detection Using Stream Descriptors},
year = {2019}}

ISPL @ ICASSP 2019

ISPL presenting its latest research findings [1, 2] at the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2019 in Brighton (UK).

[1] [doi] A. Lieto, D. Moro, F. Devoti, C. Parera, V. Lipari, P. Bestagini, and S. Tubaro, “”Hello? Who Am I Talking to?” A Shallow CNN Approach for Human vs. Bot Speech Classification,” in IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2019.
[Bibtex]
@inproceedings{lieto2019hello?,
author = {A. {Lieto} and D. {Moro} and F. {Devoti} and C. {Parera} and V. {Lipari} and P. {Bestagini} and S. {Tubaro}},
booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
doi = {10.1109/ICASSP.2019.8682743},
groups = {forensics},
title = {{"Hello? Who Am I Talking to?" A Shallow CNN Approach for Human vs. Bot Speech Classification}},
year = {2019},
Bdsk-Url-1 = {https://doi.org/10.1109/ICASSP.2019.8682743}}
[2] [doi] S. K. Yarlagadda, D. Güera, D. M. Montserrat, F. M. Zhu, E. J. Delp, P. Bestagini, and S. Tubaro, “Shadow Removal Detection and Localization for Forensics Analysis,” in IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2019.
[Bibtex]
@inproceedings{yarlagadda2019shadow,
author = {S. K. {Yarlagadda} and D. {G\"uera} and D. M. {Montserrat} and F. M. {Zhu} and E. J. {Delp} and P. {Bestagini} and S. {Tubaro}},
booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
doi = {10.1109/ICASSP.2019.8683695},
groups = {forensics},
title = {Shadow Removal Detection and Localization for Forensics Analysis},
year = {2019},
Bdsk-Url-1 = {https://doi.org/10.1109/ICASSP.2019.8683695}}

ISPL @ GTTI MMSP 2019

The GTTI-SPS Thematic Meeting on Multimedia Signal Processing gathers researchers and professionals in the domain of multimedia signal processing and its applications.

The event offers the participants the opportunity to interact and exchange ideas about scientific achievements, as well as to promote initiatives and encourage the development of the multimedia signal processing community.

GTTI MMSP 2019 is supported by the IEEE Signal Processing Society (Italian Chapter) and by the National Telecommunications and Information Technologies Group (GTTI).

ISPL team was there!

ISPL @ WIFS 2018

The IEEE International Workshop on Information Forensics and Security (WIFS) is a unique annual event organised by the IEEE Information Forensics and Security (IFS) Technical Committee of the IEEE Signal Processing Society. It is a major forum that brings researchers from related disciplines to discuss emerging challenges in different areas of information security and forensics. This workshop serves to provide a high quality forum for advancing research and development efforts in a range of areas defining e-security and forensics.

The 2018 edition of this workshop was held in Hong Kong. ISPL team was there to present its latest paper [1].

[1] [doi] N. Bonettini, L. Bondi, P. Bestagini, and S. Tubaro, “JPEG Implementation Forensics Based on Eigen-Algorithms,” in IEEE International Workshop on Information Forensics and Security (WIFS), 2018.
[Bibtex]
@inproceedings{bonettini2018jpeg,
author = {N. {Bonettini} and L. {Bondi} and P. {Bestagini} and S. {Tubaro}},
booktitle = {IEEE International Workshop on Information Forensics and Security (WIFS)},
doi = {10.1109/WIFS.2018.8630765},
groups = {forensics},
title = {{JPEG} Implementation Forensics Based on Eigen-Algorithms},
year = {2018},
Bdsk-Url-1 = {https://doi.org/10.1109/WIFS.2018.8630765}}

Video Forensics Talk @ Unicamp

Paolo Bestagini gave a talk on video forensics at the Institute of Computing (IC) of the State University of Campinas (UNICAMP) invited by Prof. Anderson Rocha.

Abstract: The recent development of multimedia devices and editing tools, together with the proliferation of video sharing websites, has made the acquisition, alteration, and diffusion of video content relatively easy tasks. As a consequence, it is possible to find more and more video sequences available on the Internet, but each of them has been potentially tampered with by anyone. It is then clear that the development of tools that enable the recovery of past history of video sequences in order to prove their origin and authenticity is more than an urgent necessity. In this talk, we discuss some of the video forensic techniques that have been proposed in the last few years. Specifically, we will focus on blind forensic methods exploiting either model-based or data-driven solutions.

Research-code thoughts

I’m sharing a few thoughts over the code development – research relationship accumulated over the past three years, in the hope these will be helpful to someone else.

  1. Our primary goal is to publish, explain, and communicate to others what our research is about. Writing down a few slides or paragraphs about the ideas we are pursuing, experimental conditions, results, feelings, and possible research directions for the future is worth investing our time. In so doing, we ensure that we go through our work thoroughly, finding out when we are doing things that could be done in a more efficient, or even completely different way.
  2. We try to be researchers, thus code is a means to reach a goal, not the goal itself.
  3. Think before writing code. At times it is enough to stop writing, start thinking, then realize that the code we were going to write was absolutely useless. Let’s think of what the output is that we would like to have, what the inputs are that we have at hand, then find the shortest path to do that.
  4. Save intermediate results. If something takes more than a few minutes, we should save the intermediate results. If every time we modify a small detail we need to re-run the whole code again and it takes hours, we are wasting our time and losing focus.
  5. The black-box is evil. We need to know what libraries and code written by others is doing. Or at least we need to be very conscious that the fault might be in the way we are using others’ code.
  6. If it takes a long time, it’s probably wrong. Check out resources usage, identify the bottleneck, and see whether the problem is in the way we wrote the code.
  7. When an algorithm works fine, let’s first publish it in a paper. Then, when the paper is submitted, let’s rewrite the code in a decent way so that it can be used in the future. Including sanity checks and tests before and after code revision. Comments/documentation is important to remind ourselves and explain to others what we have been doing.