1,721,046 research outputs found
Microphone Identification based on Spectral Entropy with Convolutional Neural Network
No full textMicrophone identification based on the intrinsic
physical features has received significant attention by the research
community in recent years. Such properties can be exploited
in security and forensics applications in order to assess the
authenticity of a certain audio track or for audio attribution.
The detection is possible since the specific characteristics of the
microphone components slightly change from one microphone to
another due to the manufacturing process. Various techniques
have been proposed to implement physical microphone identification
from the use of hand-tailored features (e.g., entropy
measure) to spectral representation (e.g., cepstral coefficients) in
combination with machine learning algorithms. In recent times,
the application of deep learning to microphone identification was
successfully demonstrated especially in comparison to shallow
machine learning algorithms. On the other hand, deep learning
requires significant computing resources especially with large
data sets, as in the case of audio recordings for microphone
identification. Then, dimensionality reduction could benefit the
computing time efficiency for this task. The proposed study
envisaged the combined use of Convolutional Neural Networks
with spectral entropy features extraction to improve time efficiency
while preserving a high identification accuracy. Spectral
features, based on Shannon entropy and Renyi entropy, are
proposed in combination with the ReliefF algorithm to implement
a dimensionality reduction of the spectral representation of the
audio signals recorded from 34 different microphones. Then, the
reduced spectral representation is fed to a custom Convolutional
Neural Network to perform the classification. The results show
that this approach is able to reduce significantly the processing
time in comparison with the state of the art while preserving a
comparable identification accuracy and an increased robustness
to the presence of noise
Smartphones identification through the built-in microphones with Convolutional Neural Network
Full text linkThe use of mobile phones or smartphones has become so widespread that most people rely on them for many services and applications like sending e-mails, checking the bank account, accessing cloud platforms, health monitoring, buying on-line and many other applications where sharing sensitive data is required. As a consequence, security functions are important in the use of smartphones, especially because most of the applications require the identification and authentication of the device in mobility. This is usually achieved through cryptographic systems but recent research studies have also investigated alternative or complementary authentication mechanisms which can be used to strengthen cryptographic methods with multi-factor authentication. In this paper, we investigate the identification and the authentication of smartphones using the intrinsic physical properties of the mobile phones built-in microphones. The possibility to identify a microphone on the basis of features extracted from audio recordings is well known in literature but it is mostly used in forensics studies and usually relies on human voice recordings. On the contrary this paper proposes a smartphone identification and authentication approach by stimulating the built-in microphone with non-voice sounds at different frequencies. An extensive data set of 32 phones was used to evaluate experimentally the proposed approach. On the basis of the proven performance of deep learning techniques, a new Convolutional Neural Network architecture is proposed both for the identification and the authentication purposes. Its performance, in comparison to other machine learning algorithms, is demonstrated in presence of different types of noises (e.g., Gaussian White noise, Babble noise and Street noise). Satisfactory results have been obtained showing that the exploitation of a fingerprint from the microphone sensor is a good choice to assess smartphone distinctiveness
Image Watermarking Backdoor Attacks in CNN-Based Classification Tasks
No full textIn these last years, neural networks are becoming the basis for different kinds of applications and this is mainly due to the stunning performances they offer. Nevertheless, all that glitters is not gold: such tools have demonstrated to be highly sensitive to malicious approaches such as gradient manipulation or the injection of adversarial samples. In particular, another kind of attack that can be performed is to poison a neural network during the training time by injecting a perceptually barely visible trigger signal in a small portion of the dataset (target class), to actually create a backdoor into the trained model. Such a backdoor can be then exploited to redirect all the predictions to the chosen target class at test time. In this work, a novel backdoor attack which resorts to image watermarking algorithms to generate a trigger signal is presented. The watermark signal is almost unperceivable and is embedded in a portion of images of the target class; two different watermarking algorithms have been tested. Experimental results carried out on datasets like MNIST and GTSRB provide satisfactory performances in terms of attack success rate and introduced distortion
A DFT-Based Analysis to Discern Between Camera and Scanned Images
No full textDigital images are generated by different sensors, understanding which kind of sensor has acquired a certain image could be crucial in many application scenarios where digital forensic techniques operate. In this
article a new methodology which permits to establish if a digital photo has been taken by a photo-camera
or has been scanned by a scanner is presented. The specific geometrical features of the sensor pattern noise
introduced by the sensor are investigated by resorting to a DFT (Discrete Fourier Transform) analysis and
consequently the origin of the digital content is assessed. Experimental results are provided to witness the
reliability of the proposed technique
Image Origin Classification Based on Social Network Provenance
Full text linkRecognizing information about the origin of a digital image has been individuated as a crucial task to be tackled by the image forensic scientific community. Understanding something on the previous history of an image could be strategic to address any successive assessment to be made on it: knowing the kind of device used for acquisition or, better, the model of the camera could focus investigations in a specific direction. Sometimes just revealing that a determined post-processing, such as an interpolation or a filtering, has been performed on an image could be of fundamental importance to go back to its provenance. This paper locates in such a context and proposes an innovative method to inquire if an image derives from a social network and, in particular, try to distinguish from, which one has been downloaded. The technique is based on the assumption that each social network applies a peculiar and mostly unknown manipulation that, however, leaves some distinctive traces on the image; such traces can be extracted to feature every platform. By resorting at trained classifiers, the presented methodology is satisfactorily able to discern different social network origins. Experimental results carried out on diverse image datasets and in various operative conditions witness that such a distinction is possible. In addition, the proposed method is also able to go back to the original JPEG quality factor the image had before being uploaded on a social network. © 2005-2012 IEEE
Microphone Identification Using Convolutional Neural Networks
No full textThe ability to identify mobile phones through their built-in components has been demonstrated in the literature for
various types of sensors including charge coupled devices (CCD)/complementary metal–oxide semiconductors (CMOS),
accelerometers, magnetometers, and microphones. The identification is performed by exploiting small but significant
differences in the electronic circuits generated during the manufacturing process. Thus, these distinctive traces become
an intrinsic property of the electronic components, which can be detected and exploited as a unique fingerprints associated
with the mobile phone. Such fingerprints can be used in various scenarios, especially in security and forensics related
applications. In this article, the identification of mobile phones through their built-in microphone by means of convolutional
neural networks (CNNs) is investigated. In this specific context, CNNs have received very limited attention by the research
community so far. An experimental dataset is created by collecting microphone responses from 34 different mobile phones.
These responses are then used to perform classification through CNNs. On different experiments, the proposed CNN is
able to provide encouraging results; in particular, the achieved identification accuracy of CNNs is superior to the one
obtained with more conventional machine learning algorithms like the K-nearest neighbor and support vector machine,
also in the presence of additive white Gaussian noise
Real-time monocular depth estimation on embedded devices: challenges and performances in terrestrial and underwater scenarios
Full text linkThe knowledge of the environmental depth is essential in multiple robotics and computer vision tasks for both terrestrial and underwater scenarios.
Recent works aim at enabling depth perception using single RGB images on deep architectures, such as convolutional neural networks and vision transformers, which are generally unsuitable for real-time inference on low-power embedded hardwares. Moreover, such architectures are trained to estimate depth maps mainly on terrestrial scenarios, due to the scarcity of underwater depth data.
Purposely, we present two lightweight architectures based on optimized MobileNetV3 encoders an a specifically designed decoder to achieve fast inferences and accurate estimations over embedded devices, and a feasibility study to predict depth maps over underwater scenarios.
Precisely, we propose the MobileNetV3_S75 configuration to infer on the 32-bit ARM CPU and the MobileNetV3_LMin for the 8-bit Edge TPU hardwares.
In underwater settings, the proposed design achieves comparable estimations with fast inference performances compared to state of the art methods.
The proposed architectures would be considered a promising approach for real-time monocular depth estimation with the aim of improving the environment perception for underwater drones, lightweight robots and internet-of-things
Why Don't You Speak?: A Smartphone Application to Engage Museum Visitors Through Deepfakes Creation
No full textIn this paper, we offer a gamification-based application for the cultural heritage sector that aims to enhance the learning and fruition of museum artworks. The application encourages users to experience history and culture in the first person, based on the idea that the artworks in a museum can tell their own story, thus improving the engagement of the museums and providing information on the artwork itself.
Specifically, we propose an application that allows museum visitors to create a deepfake video of a sculpture directly through their smartphone. More in detail, starting from a few live frames of a statue, the application generates in a short time a deepfake video where the statue talks by moving its lips synchronized with a text or audio file. The application exploits an underlying generative adversarial network technology and has been specialized on a custom statues dataset collected for the purpose. Experiments show that the generated videos exhibit great realism in the vast majority of cases, demonstrating the importance of a reliable statue face detection algorithm. The final aim of our application is to make the museum experience different, with a more immersive interaction and an engaging user experience, which could potentially attract more people to deepen classical history and culture
Acquisition source identification through a blind image classification
No full textImage forensics, besides understanding if a digital image has been forged, often aims at determining information about image origin. In particular, it could be worthy to individuate which is the kind of source (digital camera, scanner or computer graphics software) that has generated a certain photo. Such an issue has already been studied in literature, but the problem of doing that in a blind manner has not been faced so far. It is easy to understand that in many application scenarios information at disposal is usually very limited; this is the case when, given a set of L images, the authors want to establish if they belong to K different classes of acquisition sources, without having any previous knowledge about the number of specific types of generation processes. The proposed system is able, in an unsupervised and fast manner, to blindly classify a group of photos without neither any initial information about their membership nor by resorting at a trained classifier. Experimental results have been carried out to verify actual performances of the proposed methodology and a comparative analysis with two SVM-based clustering techniques has been performed too
A DVB-MHP web browser to pursue convergence between Digital Terrestrial Television and Internet
No full textIn the last decade with the growth of Interactive Digital Television (IDTV) we have seen the end of passive television. An example of this trend is Internet access through television by means of the last generation Set Top Boxes (STBs). The chance to enjoy web contents through digital television Set Top Boxes, delivering a satisfying browsing experience across this platform, could provide the opportunity to promote social inclusion and bridging the "digital divide". In this paper we present WebClimb, a web browser that would pursue an effective integration of Digital Terrestrial Television (DTT) and Internet in the DVB-MHP platform. WebClimb is a Java-based web browser that enables users to browse the web by interacting with an asy to use Graphical User Interface (GUI), driven by a common TV remote control without asking for reformatting such a content on the server side. In addition to this, the main requirement has been to design and develop an MHP browser application to be broadcast through a TV channel and not embedded in a specific device, though it could be too. Experimental results and a comparison with other possible solutions are provided
- …
