1,720,996 research outputs found
Joint near-lossless compression and watermarking of still images for authentication and tamper localization
No full textA system is presented to jointly achieve imagewatermarking and compression. The watermark is a fragile one being intended for authentication purposes. The watermarked and compressed images are fully compliant with the JPEG-LS standard, the only price to pay being a slight reduction of compression efficiency and an additional distortion that can be anyway tuned to grant a maximum preset error. Watermark detection is possible both in the compressed and in the pixel domain, thus increasing the flexibility and usability of the system. The system is expressly designed to be used in remote sensing and telemedicine applications, hence we designed it in such a way that the maximum compression and watermarking error can be strictly controlled (near-losslesscompression and watermarking). Experimental results show the ability of the system to detect tampering and to limit the peak error between the original and the processed images
Exploiting Prediction Error Inconsistencies through LSTM-based Classifiers to Detect Deepfake Videos
No full textThe ability of artificial intelligence techniques to build synthesized brand new videos or to alter the facial expression of already existing ones has been efficiently demonstrated in the literature. The identification of such new threat generally known as Deepfake, but consisting of different techniques, is fundamental in multimedia forensics. In fact this kind of manipulated information could undermine and easily distort the public opinion on a certain person or about a specific event. Thus, in this paper, a new technique able to distinguish synthetic generated portrait videos from natural ones is introduced by exploiting inconsistencies due to the prediction error in the re-encoding phase. In particular, features based on inter-frame prediction error have been investigated jointly with a Long Short-Term Memory (LSTM) model network able to learn the temporal correlation among consecutive frames. Preliminary results have demonstrated that such sequence-based approach, used to distinguish between original and manipulated videos, highlights promising performances
Metodo per introdurre un sincronismo all’interno di una immagine digitale e per il suo recupero, mediante l’uso di invarianti
No full textExploiting perceptual quality issues in countering SIFT-based Forensic methods
No full textScale Invariant Feature Transform (SIFT) has been widely employed in several image application domains, including Image Forensics (e.g. detection of copy-move forgery or near duplicates). Recently, a number of methods allowing to remove SIFT keypoints from an original image have been devised studying the problem of SIFT security against malicious procedures. Such techniques are quite effective in producing an attacked image with very few (or no) keypoints, but at the expense of an image distortion. Final perceptual quality has been taken in account very roughly so far. In this paper, effectiveness of the attacking methods is evaluated also from the side of perceptual image quality; a new version of a SIFT keypoint removal method, based on a perceptual metric, is presented and an extended series of perceptive experiments is reported. © 2014 IEEE
Adversarial image detection in deep neural networks
No full textDeep neural networks are more and more pervading many computer vision applications and in particular image classification. Notwithstanding that, recent works have demonstrated that it is quite easy to create adversarial examples, i.e., images malevolently modified to cause deep neural networks to fail. Such images contain changes unnoticeable to the human eye but sufficient to mislead the network. This represents a serious threat for machine learning methods. In this paper, we investigate the robustness of the representations learned by the fooled neural network, analyzing the activations of its hidden layers. Specifically, we tested scoring approaches used for kNN classification, in order to distinguish between correctly classified authentic images and adversarial examples. These scores are obtained searching only between the very same images used for training the network. The results show that hidden layers activations can be used to reveal incorrect classifications caused by adversarial attacks
Optical Systems Identification through Rayleigh Backscattering
Full text link: We introduce a technique to generate and read the digital signature of the networks, channels, and optical devices that possess the fiber-optic pigtails to enhance physical layer security (PLS). Attributing a signature to the networks or devices eases the identification and authentication of networks and systems thus reducing their vulnerability to physical and digital attacks. The signatures are generated using an optical physical unclonable function (OPUF). Considering that OPUFs are established as the most potent anti-counterfeiting tool, the created signatures are robust against malicious attacks such as tampering and cyber attacks. We investigate Rayleigh backscattering signal (RBS) as a strong OPUF to generate reliable signatures. Contrary to other OPUFs that must be fabricated, the RBS-based OPUF is an inherent feature of fibers and can be easily obtained using optical frequency domain reflectometry (OFDR). We evaluate the security of the generated signatures in terms of their robustness against prediction and cloning. We demonstrate the robustness of signatures against digital and physical attacks confirming the unpredictability and unclonability features of the generated signatures. We explore signature cyber security by considering the random structure of the produced signatures. To demonstrate signature reproducibility through repeated measurements, we simulate the signature of a system by adding a random Gaussian white noise to the signal. This model is proposed to address services including security, authentication, identification, and monitoring
Counter-Forensics of SIFT-based Copy-Move Detection by Means of Keypoint Classification
No full textCopy-move forgeries are very common image manipulations that are often carried out with malicious intents. Among the techniques devised by the ‘Image Forensic’ community, those relying on scale invariant feature transform (SIFT) features are the most effective ones. In this paper, we approach the copy-move scenario from the perspective of an attacker whose goal is to remove such features. The attacks conceived so far against SIFT-based forensic techniques implicitly assume that all SIFT keypoints have similar properties. On the contrary, we base our attacking strategy on the observation that it is possible to classify them in different typologies. Also, one may devise attacks tailored to each specific SIFT class, thus improving the performance in terms of removal rate and visual quality. To validate our ideas, we propose to use a SIFT classification scheme based on the gray scale histogram of the neighborhood of SIFT keypoints. Once the classification is performed, we then attack the different classes by means of class-specific methods. Our experiments lead to three interesting results: (1) there is a significant advantage in using SIFT classification, (2) the classification-based attack is robust against different SIFT implementations, and (3) we are able to impair a state-of-the-art SIFT-based copy-move detector in realistic cases
- …
