steganalysis with streamwise feature selection
DESCRIPTION
Steganalysis with Streamwise Feature Selection. Steven D. Baker University of Virginia [email protected]. Steganography: An Example. “Hello, I am the amazing Mr. Moulin!”. “Hello, I am the amazing Mr. Moulin…”. Original Image. Motivation. - PowerPoint PPT PresentationTRANSCRIPT
![Page 1: Steganalysis with Streamwise Feature Selection](https://reader035.vdocuments.net/reader035/viewer/2022062501/56815d11550346895dcb1133/html5/thumbnails/1.jpg)
Steganalysis with Streamwise Feature
Selection
Steven D. BakerUniversity of Virginia
![Page 2: Steganalysis with Streamwise Feature Selection](https://reader035.vdocuments.net/reader035/viewer/2022062501/56815d11550346895dcb1133/html5/thumbnails/2.jpg)
Steganography: An Example
Original Image “Hello, I am the amazing Mr. Moulin!”
“Hello, I am the amazing Mr. Moulin…”
![Page 3: Steganalysis with Streamwise Feature Selection](https://reader035.vdocuments.net/reader035/viewer/2022062501/56815d11550346895dcb1133/html5/thumbnails/3.jpg)
Motivation Catch bad people trying to communicate in
secret Catch good people trying to communicate in
secret? Research opportunities:
Improve detection Disrupt secret communication without harming
legitimate image sharing Improve theoretical guarantees
![Page 4: Steganalysis with Streamwise Feature Selection](https://reader035.vdocuments.net/reader035/viewer/2022062501/56815d11550346895dcb1133/html5/thumbnails/4.jpg)
Triangle of Peril
Secrecy
Robustness
Rate
Detectable
Useless
Target region
![Page 5: Steganalysis with Streamwise Feature Selection](https://reader035.vdocuments.net/reader035/viewer/2022062501/56815d11550346895dcb1133/html5/thumbnails/5.jpg)
Theoretical work in Steganography Complexity theory
Provably Secure Steganography [Hopper et al.] Information theory
An Information-Theoretic Model for Steganography [Cachin]
Perfectly Secure Steganography [Wang and Moulin] Basic conclusion: perfect security means useless
rate No available, practical algorithm allows smooth
adjustment of rate, robustness, and secrecy*
![Page 6: Steganalysis with Streamwise Feature Selection](https://reader035.vdocuments.net/reader035/viewer/2022062501/56815d11550346895dcb1133/html5/thumbnails/6.jpg)
Method of Wang and Moulin
Steg and coverimages Wavelet transform
PDFCharacteristic Function
Moments(Feature generation)Feature SelectionTrainingClassification
![Page 7: Steganalysis with Streamwise Feature Selection](https://reader035.vdocuments.net/reader035/viewer/2022062501/56815d11550346895dcb1133/html5/thumbnails/7.jpg)
Let Intel do the work Can we combine existing features to form
useful new features? Have a computer separate the useless
features from the good ones Do this in a suboptimal but very fast way, so
that you can evaluate loads of features, more than there are observations
Streamwise Feature Selection [Zhou et al.]
![Page 8: Steganalysis with Streamwise Feature Selection](https://reader035.vdocuments.net/reader035/viewer/2022062501/56815d11550346895dcb1133/html5/thumbnails/8.jpg)
Feature generation/selection(Alpha-investing)
?
Reject featureDecrease wealth
Add feature
Increase wealth
More features, more time?
Generate feature
![Page 9: Steganalysis with Streamwise Feature Selection](https://reader035.vdocuments.net/reader035/viewer/2022062501/56815d11550346895dcb1133/html5/thumbnails/9.jpg)
Feature generation Pair-wise ratios Pair-wise differences Principal Component Analysis Untested possibilities:
Log Square root Nonsmooth Nonnegative Matrix Factorization
![Page 10: Steganalysis with Streamwise Feature Selection](https://reader035.vdocuments.net/reader035/viewer/2022062501/56815d11550346895dcb1133/html5/thumbnails/10.jpg)
Experimental data (Shi et al.) CorelDraw images
~1000 images 78 Original features > 6000 generated features
Steganographic techniques Cox et al. (SS) Piva et al. (SS) Huang et al. (SS) Generic QIM Generic LSB
![Page 11: Steganalysis with Streamwise Feature Selection](https://reader035.vdocuments.net/reader035/viewer/2022062501/56815d11550346895dcb1133/html5/thumbnails/11.jpg)
Results: ROC
![Page 12: Steganalysis with Streamwise Feature Selection](https://reader035.vdocuments.net/reader035/viewer/2022062501/56815d11550346895dcb1133/html5/thumbnails/12.jpg)
Results: Model Complexity
![Page 13: Steganalysis with Streamwise Feature Selection](https://reader035.vdocuments.net/reader035/viewer/2022062501/56815d11550346895dcb1133/html5/thumbnails/13.jpg)
Results: AUC
![Page 14: Steganalysis with Streamwise Feature Selection](https://reader035.vdocuments.net/reader035/viewer/2022062501/56815d11550346895dcb1133/html5/thumbnails/14.jpg)
Questions?