Recent studies exposed the weaknesses of scale-invariant feature transform (SIFT)-based analysis by removing\r\nkeypoints without significantly deteriorating the visual quality of the counterfeited image. As a consequence, an\r\nattacker can leverage on such weaknesses to impair or directly bypass with alarming efficacy some applications that\r\nrely on SIFT. In this paper, we further investigate this topic by addressing the dual problem of keypoint removal, i.e.,\r\nthe injection of fake SIFT keypoints in an image whose authentic keypoints have been previously deleted. Our interest\r\nstemmed from the consideration that an image with too few keypoints is per se a clue of counterfeit, which can be\r\nused by the forensic analyst to reveal the removal attack. Therefore, we analyse five injection tools reducing the\r\nperceptibility of keypoint removal and compare them experimentally. The results are encouraging and show that\r\ninjection is feasible without causing a successive detection at SIFT matching level. To demonstrate the practical\r\neffectiveness of our procedure, we apply the best performing tool to create a forensically undetectable copy-move\r\nforgery, whereby traces of keypoint removal are hidden by means of keypoint injection.
Loading....