• Farooq Sunar Mahammad
• N. Varshitha Reddy
• S.V. Navya Sahithi
• L.V. Kowsalya
• V.Chinmayi

The data driven image manipulation detection in the presence of attacker with limited knowledge about the detector. At first, we imagine that the attacker knows the architecture, training data and class of features that detector depend on. The analyst designs the detector that depends on subset of features chosen at random in the class in order to get an advantage in his race of arms with the attacker. Given its ignorance about the exact feature set, the attacker attacks a version of detector is based on the entire feature set. By this way the effectiveness of the attacker decreases, because there is no guarantee for the attacker that his attack is successful as the detector is working on full feature space. Thus, random feature selection increases the security of the detector for negligible loss of performance in the absence of attacks. We focus on two specific kinds of image manipulations, namely Adaptive histogram equalization and Median filtering.

Detectors, Secret Key, Image Forensics, Feature Extraction.

"RFS for detecting Image Manipulation", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.5, Issue 9, page no.954-959, September-2018, Available :http://www.jetir.org/papers/JETIR1809933.pdf

"RFS for detecting Image Manipulation", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.5, Issue 9, page no. pp954-959, September-2018, Available at : http://www.jetir.org/papers/JETIR1809933.pdf