Search

This study investigates the application of steganography for enhancing network security by detecting and promptly eliminating malicious packets to prevent flooding and consequent denial of service attacks while also identifying malicious equipment. The paper discusses foundational concepts such as the prisoner’s dilemma, covert channels, qualitative metrics, and existing steganography techniques in computer communications. An architecture was developed to assess the effectiveness of this solution, and experiments were conducted, with their results presented. This contribution leverages established steganographic principles and seamlessly integrates with widely adopted IPsec protocols, offering a solution to improve covert communication within computer networks.

This paper presents the application of self-supervised deep contrastive learning in clustering signals detected in the wideband RF spectrum, presented in the form of spectrograms. Radio clustering is a method of searching for similar signals within the analyzed part of the radio spectrum. Typically, it is based on one or several specific parameters processed from the signal in a given channel. The authors propose a slightly different, innovative approach; thanks to the self-supervised learning of neural networks, there is no need to define specific parameters, and the feature vector, enabling comparison of Euclidean distances between signals, is generated by a deep neural network trained using a contrastive loss function on a dataset containing different radio modulations. The authors describe self-supervised solutions based on contrastive learning and the methods of signal segmentation and augmentation. The training process utilizes a custom database and the Resnet-50 network with a contrastive cost function. Radio clustering is used for autonomous spectrum analysis across wide frequency ranges and enables, among other things, the detection of tactical radio stations operating with widely dispersed frequency-hopping or a significant reduction in computational power required for real-time analysis of a large number of radio signals.

The proliferation of “Deep fake” technologies, particularly those facilitating face-swapping in images or videos, poses significant challenges and opportunities in digital media manipulation. Despite considerable advancements, existing methodologies often struggle with maintaining visual coherence, especially in preserving background features and ensuring the realistic integration of identity traits. This study introduces a novel face replacement model that leverages a singular framework to address these issues, employing the Adaptive Attentional Denormalization mechanism from FaceShifter and integrating identity features via ArcFace and BiSeNet for enhanced attribute extraction. Key to our approach is the utilization of Fast GAN, optimizing the training efficiency of our model on relatively small datasets. We demonstrate the model’s efficacy in generating convincing face swaps with high fidelity, showcasing a significant improvement in blending identities seamlessly with the original background context. Our findings contribute to visual deepfake generation by enhancing realism and training efficiency but also highlight the potential for applications where authentic visual representation is crucial.

The paper presents a practical implementation of the non-classified data hiding system (NDHS) understood as a military platform for information warfare that takes advantage of the hidden data transmission for voice connections in order to gain informational lead over a potential enemy. The NDHS performs here as a botnet network that is managed by the hidden transmission controller referred to as the master resident. Research studies are dedicated to investigation of various connections in heterogeneous links as well as functionalities of such components as hidden protocol bridges and the master resident

The paper describes the method intended to authenticate identity of a VoIP subscriber with use of the data hiding technique that is specifically implemented by means of the echo hiding method. The scope includes presentation of experimental results related to transmission of information via a hidden channel with use of the SIP/SDP signalling protocol as well as results of subjective assessment on quality of a signal with an embedded watermark.

This study is a survey of sound source localization and detection methods. The study provides a detailed classification of the methods used in the fields of science mentioned above. It classifies sound source localization systems based on criteria found in the literature. Moreover, an analysis of classic methods based on the propagation model and methods based on machine learning and deep learning techniques has been carried out. Attention has been paid to providing the most detailed information on the possibility of using physical phenomena, mathematical relationships, and artificial intelligence to determine sound source localization. Additionally, the article underscores the significance of these methods within both military and civil contexts. The study culminates with a discussion of forthcoming trends in the realms of acoustic detection and localization. The primary objective of this research is to serve as a valuable resource for selecting the most suitable approach within this domain.

Wideband spectrum sensing plays a crucial role in various wireless communication applications. Traditional methods, such as energy detection with thresholding, have limitations like detecting signals with low signal-to-noise ratio (SNR). This article proposes a novel deep learning-based approach for RF signal detection in the wideband spectrum. The objective is to accurately estimate the noise distribution in a wideband radio spectrogram and improve the detection performance by substracting it. The proposed method utilizes convolutional neural networks to analyze radio spectrograms. Model evaluation demonstrates that the RFROI-CNN approach outperforms the traditional energy detection with thresholding method by achieving significantly better detection results, even up to 6 dB, and expanding the capabilities of wideband spectrum sensing systems. The proposed approach, with its precise estimation of noise distribution and consideration of neighboring signal power values, proves to be a promising solution for RF signal detection.

Deep Fake technology has developed rapidly in its generation and detection in recent years. Researchers in both fields are outpacing each other in their axes achievements. The works use, among other methods, autoencoders, generative adversarial networks, or other algorithms to create fake content that is resistant to detection by algorithms or the human eye. Among the ever-increasing number of emerging works, a few can be singled out that, in their solutions and robustness of detection, contribute significantly to the field. Despite the advancement of emerging generative algorithms, the fields are still left for further research. This paper will briefly introduce the fundamentals of some the latest Face Swap Deep Fake algorithms.

Voice conversion is a process where the essence of a speaker’s identity is seamlessly transferred to another speaker, all while preserving the content of their speech. This usage is accomplished using algorithms that blend speech processing techniques, such as speech analysis, speaker classification, and vocoding. The cutting-edge voice conversion technology is characterized by deep neural networks that effectively separate a speaker’s voice from their linguistic content. This article offers a comprehensive overview of the development status of this area of science based on the current state-of-the-art voice conversion methods.

This paper presents a method for the transparent, robust, and highly capacitive watermarking of video signals using an information mapper. The proposed architecture is based on the use of deep neural networks to embed the watermark in the luminance channel in the YUV color space. An information mapper was used to enable the transformation of a multi-bit binary signature of varying capacitance reflecting the entropy measure of the system into a watermark embedded in the signal frame. To confirm the effectiveness of the method, tests were carried out for video frames with a resolution of 256 × 256 pixels, with a watermark capacity of 4 to 16,384 bits. Transparency metrics (SSIM and PSNR) and a robustness metric—the bit error rate (BER)—were used to assess the performance of the algorithms.

The paper presents a comparison of automatic skin cancer diagnosis algorithms based on analyses of skin lesions photos. Two approaches are presented: the first one is based on the extraction of features from images using simple feature descriptors, and then the use of selected machine learning algorithms for the purpose of classification, and the second approach uses selected algorithms belonging to the subgroup of machine learning—deep learning, i.e., convolutional neural networks (CNN), which perform both the feature extraction and classification in one algorithm. The following algorithms were analyzed and compared: Logistic Regression, k-Nearest Neighbors, Naive Bayes, Decision Tree, Random Forest, and Support Vector Machine, and four CNN–VGG-16, ResNet60, InceptionV3, and Inception-ResNetV2 In the first variant, before the classification process, the image features were extracted using 4 different feature descriptors and combined in various combinations in order to obtain the most accurate image features vector, and thus the highest classification accuracy. The presented approaches have been validated using the image dataset from the ISIC database, which includes data from two categories—benign and malignant skin lesions. Common machine learning metrics and saved values of training time were used to evaluate the effectiveness and the performance (computational complexity) of the algorithms.

This article presents a method for transparent watermarking of high-capacity watermarked video under H.265/HEVC (High-Efficiency Video Coding) compression conditions while maintaining high-quality encoded image. The aim of this paper is to present a method for watermark embedding using neural networks under conditions of subjecting video to lossy compression of the HEVC codec using the YUV420p color model chrominance channel for watermarking. This paper presents a method for training a deep neural network to embed a watermark when a compression channel is present. The discussed method is characterized by high accuracy of the video with an embedded watermark compared to the original. The PSNR (peak signal-to-noise ratio) values obtained are over 44 dB. The watermark capacity is 96 bits for an image with a resolution of 128 × 128. The method enables the complete recovery of a watermark from a single video frame compressed by the HEVC codec within the range of compression values defined by the CRF (constant rate factor) up to 22.

In this article, a superposition-based covert channel and its demodulator were proposed and examined. As a covert waveform, an 8FSK modulation was selected. The impact of the channel estimation error and resulting imperfect SIC operation (successive interference cancelation) on the covert information demodulation process was considered. Especially for this imperfection, an NN-based demodulator was proposed. The superiority of this solution over the traditional 8FSK correlator-based receiver was examined for various cases, including the hard- and soft-decision detectors. It was proven that, although NN does not provide BER values equal to zero, even for the perfect SIC, it generally overcomes the traditional correlator-based 8FSK demodulator. Simulation results showed that the NN-base demodulator, in the case of additional covert channel coding, provides error-free demodulation, even for four-times greater channel gain error.

This paper presents a method of high-capacity and transparent watermarking based on the usage of deep neural networks with the adjustable subsquares properties algorithm to encode the data of a watermark in high-quality video using the H.265/HEVC (High-Efficiency Video Coding) codec. The aim of the article is to present a method of embedding a watermark in a video with HEVC codec compression by making changes in a video in a way that is not noticeable to the naked eye. The method presented here is characterised by focusing on ensuring the accuracy of the original image in relation to the watermarked image, providing the transparency of the embedded watermark, while ensuring its survival after compression by the HEVC codec. The article includes a presentation of the practical results of watermark embedding with a built-in variation mechanism of its capacity and resistance, thanks to the adjustable subsquares properties algorithm. The obtained PSNR (peak signal-to-noise ratio) results are at the level of 40 dB or better. There is the possibility of the complete recovery of a watermark from a single frame compressed in the CRF (constant rate factor) range of up to 16, resulting in a BER (bit error rate) equal to 0 for the received watermark.

The proposed StegoFrameOrder (SFO) method enables the transmission of covert data in wireless computer networks exploiting non-deterministic algorithms of medium access (such as the distributed coordination function), especially in IEEE 802.11 networks. Such a covert channel enables the possibility of leaking crucial information outside secured network in a manner that is difficult to detect. The SFO method embeds hidden bits of information in the relative order of frames transmitted by wireless terminals operating on the same radio channel. The paper presents an idea of this covert channel, its implementation, and possible variants. The paper also discusses implementing the SFO method in a real environment and the experiments performed in the real-world scenario.

In localization systems based on the emission of reference radio signals, an important issue related to the reliability of sensor operation is the problem of operating time and power of the emitted reference radio signal. There are many localization methods that have proven useful in practice and that use a reference radio signal for this purpose. In the issue of determining the location of radio emitters, various radio signal propagation models are used to determine the effective range and distance of the sensor-receiver from the radio emitter. This paper presents an adaptive power control algorithm for a transmitter, as a reference emitter, operating in power-saving mode. An important advantage of the presented solution is the adjustment of the localization system accuracy at the assumed level of energy radiated by radio emitters based on the RSSI signal received power estimation.

We consider the question of preservation of Baire and weakly Baire category under images and preimages of certain kind of functions. It is known that Baire category is preserved under image of quasi-continuous feebly open surjections. In order to extend this result, we introduce a strictly larger class of quasi-continuous functions, i.e. the class of quasi-interior continuous functions. We show that Baire and weakly Baire categories are preserved under image of feebly open quasi-interior continuous surjections. We also give a new definition for countably fiber-completeness of a function. We prove that Baire category is preserved under inverse image of a countably fiber-complete function provided that it is feebly open and feebly continuous.

Steganography is a technique that makes it possible to hide additional information (payload) in the original signal (cover work). This paper focuses on hiding information in a speech signal. One of the major problems with steganographic systems is ensuring synchronization. The paper presents four new and effective mechanisms that allow achievement of synchronization on the receiving side. Three of the developed methods of synchronization operate directly on the acoustic signal, while the fourth method works in the higher layer, analyzing the structure of the decoded steganographic data stream. The results of the research concerning both the evaluation of signal quality and the effectiveness of synchronization are presented. The signal quality was assessed based on both objective and subjective methods. The conducted research confirmed the effectiveness of the developed methods of synchronization during the transmission of steganographic data in the VHF radio link and in the VoIP channel.

In recent years, there has been a noticeable increase in interest in the possibilities of embedding additional data in the constellation of an already existing information signal in radio technology. This solution more precisely is based on adding a low power signal (or signals) to a stronger signal (cover). As will be described in the article, this technique is used in numerous radio communication areas, such as watermarking, covert channel creation, and multiple access techniques. Typically, those areas are considered as independent research topics. Our comparison suggests that these areas are closely related. In this article, a comprehensive survey of the implementation of signal superposition is conducted with an emphasis on the similarities and differences between individual solutions. Since the nature of the signal model entails certain problems in the security area, we provide the reader with a review of the state-of-the-art research on this topic, including the PLS (physical layer security) and LPD (low probability of detection) issues.

Odpowiednio wczesne zabezpieczenie krytycznych systemów infrastruktury na potencjalnie groźne ataki typu voice spoofing jest warunkowane opracowaniem skutecznych metod i istnieniem dedykowanych rozwiązań technicznych. Metody ataków i obrony przed impersonizacją skupiają się zasadniczo na dwóch obszarach: zmianie głosu abonenta na inny głos (wirtualny lub innej osoby) oraz nieautoryzowanej edycji komunikatów głosowych. W nowych generacjach ataków na łącza telefoniczne, w których następuje zmiana głosu mówcy w czasie rzeczywistym lub odtwarzany jest uprzednio spreparowany komunikat, stosuje się metody obrony polegające na m.in. weryfikacji wspólnie posiadanej wiedzy lub posiadanego klucza.

Using a game-theoretic characterization of Baire spaces, conditions upon the domain and the range are given to ensure a fat set C(f) of points of continuity in the sets of type X×{y}, y∈Y for certain almost separately continuous functions f:X×Y→Z. These results (especially Theorem B) generalize Mibu's. First Theorem, previous theorems of the author, answers one of his problems as well as they are closely related to some other results of Debs [1] and Mibu [2].

We proposed an OFDM and watermarking based technology system for correspondent identity verification (CIVS) in military telecommunication digital channels. Correspondent personal identity signature (CPIS) is represented by digital watermark. The main idea of this system solution is to verify the end user who sends acoustic signal, e.g., speech, music, etc., via Internet, HF/UHF radio, modem, etc. OFDM modulation scheme is used to prepare secret digital signature. This signature is a single-use secret key used for correspondent verification, thus binary sequence of that key is changing for every session. We describe transmitter and receiver block scheme. The results of experiments for both ideal and degraded signals are described in details too. The results are summarized with comments and conclusion.

This paper describes a new method of frequency offset correction to improve clock stability in communication systems where the temporary drift or jitter of phase angle is not accepted. This method bases on coherent spectral averaging with a special phase scanning algorithm. Achieved results show that proposed method is effective for strongly degraded signals. Method is useful for precise phase angle reconstruction in these systems where clock stability of the transceiver and receiver is insufficient.

The purpose of this note is to study modifications of the Euclidean metric on IR with the following property. There is a monotone sequence of closed balls with empty intersection.