Robust Machine Learning Algorithms and Systems for Detection and Mitigation of Adversarial Attacks and Anomalies Proceedings of a Workshop (2019) / Chapter Skim
Currently Skimming:
3 Adversarial Attacks
3 Adversarial Attacks
Pages 7-12
The Chapter Skim interface presents what we've algorithmically identified as the most significant single chunk of text within every page in the chapter.
Select key terms on the right to highlight them within pages of the chapter.
From page 7... ...
He hopes that MediFor will raise awareness in the research community to develop software and techniques for automatically detecting manipulations in media. To highlight the process of manually assessing an image, he showed the example of a manipulated image of a hovercraft landing and described how one can use the manual indicators such as the wakes, shadow consistency, and sun angle to determine the integrity of the image.
|
From page 8... ...
Turek described important digital, physical, and semantic integrity and integrity reasoning indicators. Each description consisted of the underlying questions, examples of manipulation detection, the previous state of the art, work of the MediFor researchers, and challenges.
|
From page 9... ...
Turek presented the GAN challenge that looked at manipulation detection and localization task on modified data. The challenge used three data sets: the full image set, containing images partially altered by GANs; the crop image set, which are completely generated by GANs or are real; and the video set, including deepfakes.
|
From page 10... ...
He also responded to a question about whether downstream editing or other tools degrade sensor signatures; Turek responded yes, but sometimes they leave their own "fingerprints." He said that MediFor researchers are investigating how to identify software packages that have manipulated images or video. He added that the camera ID can often be recovered, even under certain levels of compression and manipulation; however, it does degrade with the removal of the noise artifacts.
|
From page 11... ...
In the final example, Farid showed a video in which former President Obama appears to be talking, but in reality actor Jordan Peele is talking. This is an example of a deepfake.
|
From page 12... ...
Farid responded that he has started to question his beliefs about publishing work openly and suggested that holding back code is a good compromise because new technologies can be assimilated into generative adversarial networks quickly. An audience participant expressed concern about finding the right balance with so many competing objectives in maintaining the integrity of communication, while another audience participant cautioned that too much obscurity of information could lead to an inability to see what our adversaries are doing.
|
Key Terms
This material may be derived from roughly machine-read images, and so is provided only to facilitate research.
More
information on Chapter Skim is available.