Biblio

Unsupervised cross-domain NER task aims to solve the issues when data in a new domain are fully-unlabeled. It leverages labeled data from source domain to predict entities in unlabeled target domain. Since training models on large domain corpus is time-consuming, in this paper, we consider an alternative way by introducing syntactic dependency structure. Such information is more accessible and can be shared between sentences from different domains. We propose a novel framework with dependency-aware GNN (DGNN) to learn these common structures from source domain and adapt them to target domain, alleviating the data scarcity issue and bridging the domain gap. Experimental results show that our method outperforms state-of-the-art methods.

Recent studies have demonstrated the lack of robustness of image reconstruction networks to test-time evasion attacks, posing security risks and potential for misdiagnoses. In this paper, we evaluate how vulnerable such networks are to training-time poisoning attacks for the first time. In contrast to image classification, we find that trigger-embedded basic backdoor attacks on these models executed using heuristics lead to poor attack performance. Thus, it is non-trivial to generate backdoor attacks for image reconstruction. To tackle the problem, we propose a bi-level optimization (BLO)-based attack generation method and investigate its effectiveness on image reconstruction. We show that BLO-generated back-door attacks can yield a significant improvement over the heuristics-based attack strategy.

Solidly mounted resonators (SMRs) built on dielectric acoustic reflectors can save several fabrication steps as well as avoid undesired parasitic effects when exciting extended electrodes via capacitive coupling. In this work we manufacture and measure the frequency response of AlN-based SMRs built on 7-layer ZnO/SiO2 acoustic reflectors with SiO2 working as low impedance material and ZnO as high impedance material. After applying a 700°C treatment, their frequency response is measured again and compared with the pre-treatment measurements.

The achievable bandwidth in ladder acoustic filters is strictly limited by the electromechanical coupling coefficient (k;) in conventional ladder-acoustic filters. Furthermore, their out-of-band rejection is inherently weak due to the frequency responses of the shunt or series-connected acoustic resonators. This work proposes a coupling-matrix-based solution for both issues by employing acoustic and electromagnetic resonators within the same filter prototype using prescribed Chebyshev responses. It has been shown that significantly much wider bandwidths, that cannot be achieved with acoustic-only filters, can be obtained. An important strength of the proposed method is that a filter with a particular FBW can be designed with a wide range of acoustic resonators with different k; values. An 14 % third-order asymmetrical-response filter is designed and fabricated using electromagnetic resonators and an acoustic resonator with a k; of 3.5 %.

In this paper, we present the architecture of a Smart Industry inspired platform designed for Agriculture 4.0 applications and, specifically, to optimize an ecosystem of SW and HW components for animal repelling. The platform implementation aims to obtain reliability and energy efficiency in a system aimed to detect, recognize, identify, and repel wildlife by generating specific ultrasound signals. The wireless sensor network is composed of OpenMote hardware devices coordinated on a mesh network based on the 6LoWPAN protocol, and connected to an FPGA-based board. The system, activated when an animal is detected, elaborates the data received from a video camera connected to FPGA-based hardware devices and then activates different ultrasonic jammers belonging to the OpenMotes network devices. This way, in real-time wildlife will be progressively moved away from the field to be preserved by the activation of specific ultrasonic generators. To monitor the daily behavior of the wildlife, the ecosystem is expanded using a time series database running on a Cloud platform.

Recent advancements of spatial audio technologies to enhance human’s emotional and immersive experiences are gathering attention. Many studies are clarifying the neural mechanisms of acoustic spatial perception; however, they are limited to the evaluation of mechanisms using basic sound stimuli. Therefore, it remains challenging to evaluate the experience of actual music contents and to verify the effects of higher-order neurophysiological responses including a sense of immersive and realistic experience. To investigate the effects of spatial audio experience, we verified the psychophysiological responses of immersive spatial audio experience using sound field synthesis (SFS) technology. Specifically, we evaluated alpha power as the central nervous system activity, heart rate/heart rate variability and skin conductance as the autonomic nervous system activity during an acoustic experience of an actual music content by comparing stereo and SFS conditions. As a result, statistically significant differences (p \textbackslashtextless 0.05) were detected in the changes in alpha wave power, high frequency wave power of heart rate variability (HF), and skin conductance level (SCL) among the conditions. The results of the SFS condition showed enhanced the changes in alpha power in the frontal and parietal regions, suggesting enhancement of emotional experience. The results of the SFS condition also suggested that close objects are grouped and perceived on the basis of the spatial proximity of sounds in the presence of multiple sound sources. It is demonstrating that the potential use of SFS technology can enhance emotional and immersive experiences by spatial acoustic expression.

Autonomous vehicles increasingly exploit computer-vision-based object detection systems to perceive environments and make critical driving decisions. To increase the quality of images, image stabilizers with inertial sensors are added to alleviate image blurring caused by camera jitters. However, such a trend opens a new attack surface. This paper identifies a system-level vulnerability resulting from the combination of the emerging image stabilizer hardware susceptible to acoustic manipulation and the object detection algorithms subject to adversarial examples. By emitting deliberately designed acoustic signals, an adversary can control the output of an inertial sensor, which triggers unnecessary motion compensation and results in a blurred image, even if the camera is stable. The blurred images can then induce object misclassification affecting safety-critical decision making. We model the feasibility of such acoustic manipulation and design an attack framework that can accomplish three types of attacks, i.e., hiding, creating, and altering objects. Evaluation results demonstrate the effectiveness of our attacks against four academic object detectors (YOLO V3/V4/V5 and Fast R-CNN), and one commercial detector (Apollo). We further introduce the concept of AMpLe attacks, a new class of system-level security vulnerabilities resulting from a combination of adversarial machine learning and physics-based injection of information-carrying signals into hardware.

The front-end text processing module is considered as an essential part that influences the intelligibility and naturalness of a Mandarin text-to-speech system significantly. For commercial text-to-speech systems, the Mandarin front-end should meet the requirements of high accuracy and low time latency while also ensuring maintainability. In this paper, we propose a universal BERT-based model that can be used for various tasks in the Mandarin front-end without changing its architecture. The feature extractor and classifiers in the model are shared for several sub-tasks, which improves the expandability and maintainability. We trained and evaluated the model with polyphone disambiguation, text normalization, and prosodic boundary prediction for single task modules and multi-task learning. Results show that, the model maintains high performance for single task modules and shows higher accuracy and lower time latency for multi-task modules, indicating that the proposed universal front-end model is promising as a maintainable Mandarin front-end for commercial applications.

Wireless communication systems are inherently vulnerable to adversarial attacks since malevolent jammers might jam and disrupt the legitimate transmission intentionally. Of particular interest are so- called denial-of-service (DoS) attacks in which the jammer is able to completely disrupt the communication. Accordingly, it is of crucial interest for the legitimate users to detect such DoS attacks. Turing machines provide the fundamental limits of today's digital computers and therewith of the traditional signal processing. It has been shown that these are incapable of detecting DoS attacks. This stimulates the question of how powerful the signal processing must be to enable the detection of DoS attacks. This paper investigates the general computation framework of Blum-Shub-Smale machines which allows the processing and storage of arbitrary reals. It is shown that such real number signal processing then enables the detection of DoS attacks.

Underwater wireless sensor network(UWSN) is an emerging technology for exploring and research inside the ocean. Since it is somehow similar to the normal wireless network, which uses radio signals for communication purposes, while UWSN uses acoustic for communication between nodes inside the ocean and sink nodes. Due to unattended areas and the vulnerability of acoustic medium, UWNS are more prone to various malicious attacks like Sybil attack, Black-hole attack, Wormhole attack, etc. This paper analyzes blackhole attacks in UWSN and proposes an algorithm to mitigate blackhole attacks by forming clusters of nodes and selecting coordinator nodes from each cluster to identify the presence of blackholes in its cluster. We used public-key cryptography and the challenge-response method to authenticate and verify nodes.

In this paper, we propose a framework for privacy-preserving approximate near neighbor search via stochastic sparsifying encoding. The core of the framework relies on sparse coding with ambiguation (SCA) mechanism that introduces the notion of inherent shared secrecy based on the support intersection of sparse codes. This approach is ‘fairness-aware’, in the sense that any point in the neighborhood has an equiprobable chance to be chosen. Our approach can be applied to raw data, latent representation of autoencoders, and aggregated local descriptors. The proposed method is tested on both synthetic i.i.d data and real image databases.

Photo Response Non-Uniformity (PRNU) noise obtained from images or videos is used as a camera fingerprint to attribute visual objects captured by a camera. The PRNU-based source attribution method, however, fails when there is misalignment between the fingerprint and the query object. One example of such a misalignment, which has been overlooked in the field, is caused by the in-camera resizing technique that a video may have been subjected to. This paper investigates the attribution of visual media in the context of matching a video query object to an image fingerprint or vice versa. Specifically this paper focuses on improving camera attribution performance by taking into account the effects of binning, a commonly used in-camera resizing technique applied to video. We experimentally show that the True Positive Rate (TPR) obtained when binning is considered is approximately 3% higher.

The research proposal discloses a novel drone-based ad-hoc network that leverages acoustic information for power plant surveillance and utilizes a secure blockchain model for protecting the integrity of drone communication over the network. The paper presents a vision for the drone-based networks, wherein drones are employed for monitoring the complex power plant machinery. The drones record acoustic information generated by the power plants and detect anomalies or deviations in machine behavior based on collected acoustic data. The drones are linked to distributed network of computing devices in possession with the plant stakeholders, wherein each computing device maintains a chain of data blocks. The chain of data blocks represents one or more transactions associated with power plants, wherein transactions are related to high risk auditory data set accessed by the drones in an event of anomaly or machine failure. The computing devices add at least one data block to the chain of data blocks in response to valid transaction data, wherein the transaction data is validated by the computing devices owned by power plant personnel.

The two-factor authentication (2FA) has drawn increasingly attention as the mobile devices become more prevalent. For example, the user's possession of the enrolled phone could be used by the 2FA system as the second proof to protect his/her online accounts. Existing 2FA solutions mainly require some form of user-device interaction, which may severely affect user experience and creates extra burdens to users. In this work, we propose Proximity-Echo, a secure 2FA system utilizing the proximity of a user's enrolled phone and the login device as the second proof without requiring the user's interactions or pre-constructed device fingerprints. The basic idea of Proximity-Echo is to derive location signatures based on acoustic beep signals emitted alternately by both devices and sensing the echoes with microphones, and compare the extracted signatures for proximity detection. Given the received beep signal, our system designs a period selection scheme to identify two sound segments accurately: the chirp period is the sound segment propagating directly from the speaker to the microphone whereas the echo period is the sound segment reflected back by surrounding objects. To achieve an accurate proximity detection, we develop a new energy loss compensation extraction scheme by utilizing the extracted chirp periods to estimate the intrinsic differences of energy loss between microphones of the enrolled phone and the login device. Our proximity detection component then conducts the similarity comparison between the identified two echo periods after the energy loss compensation to effectively determine whether the enrolled phone and the login device are in proximity for 2FA. Our experimental results show that our Proximity-Echo is accurate in providing 2FA and robust to both man-in-the-middle (MiM) and co-located attacks across different scenarios and device models.

Most of existing audio fingerprinting systems have limitations to be used for high-specific audio retrieval at scale. In this work, we generate a low-dimensional representation from a short unit segment of audio, and couple this fingerprint with a fast maximum inner-product search. To this end, we present a contrastive learning framework that derives from the segment-level search objective. Each update in training uses a batch consisting of a set of pseudo labels, randomly selected original samples, and their augmented replicas. These replicas can simulate the degrading effects on original audio signals by applying small time offsets and various types of distortions, such as background noise and room/microphone impulse responses. In the segment-level search task, where the conventional audio fingerprinting systems used to fail, our system using 10x smaller storage has shown promising results. Our code and dataset are available at https://mimbres.github.io/neural-audio-fp/.

In recent years, one of the important and interesting tasks has become the protection of civilian and military objects from unmanned aerial vehicles (UAVs) carrying a potential threat. To solve this problem, it is required to detect UAVs and activate protective systems. UAVs can be represented as aerodynamic objects of the monoplane or multicopter type with acoustic fingerprints. In this paper we consider algorithm for UAV acoustic detection and recognition system. Preliminary results of analysis of experimental data show effectiveness of proposed approach.

This paper presents a distributed adaptive algorithm for node-specific sound zoning in a wireless acoustic sensor and actuator network (WASAN), based on a network-wide acoustic contrast control (ACC) method. The goal of the ACC method is to simultaneously create node-specific zones with high signal power (bright zones) while minimizing power leakage in other node-specific zones (dark zones). To obtain this, a network-wide objective involving the acoustic coupling between all the loudspeakers and microphones in the WASAN is proposed where the optimal solution is based on a centralized generalized eigenvalue decomposition (GEVD). To allow for distributed processing, a gradient based GEVD algorithm is first proposed that minimizes the same objective. This algorithm can then be modified to allow for a fully distributed implementation, involving in-network summations and simple local processing. The algorithm is referred to as the distributed adaptive gradient based ACC algorithm (DAGACC). The proposed algorithm outperforms the non-cooperative distributed solution after only a few iterations and converges to the centralized solution, as illustrated by computer simulations.

In this paper, an acoustic resonator with frequency \textbackslashtextgreater 5 GHz is designed, implemented, and measured with electromechanical coupling exceeding 15% and low temperature dependence compared to conventional Lamb-wave resonators. The acoustic resonator is optimized for the S4 mode Lamb waves in a bi-morph composed of Lithium Niobate and Silicon Dioxide. The resonator optimization is based on adjusting the thickness of different materials in the bimorph to maximize the coupling and minimize temperature dependence simultaneously. The achieved specifications are adequate for 5G sub-6 GHz frequency band n46 in addition to Wi-Fi new bands between 5 and 6 GHz.

The position information leakage of under-water sensor networks has been widely concerned. However, the underwater environment has unique characteristics compared with the terrestrial environment, for example, the asynchronous clock, stratification compensation. Therefore, the privacy preserving localization algorithm for terrestrial is not suitable. At present, the proposed privacy preserving localization algorithm is at the cost of reducing the localization accuracy and increasing the complexity of the algorithm. In this paper, a privacy preserving localization algorithm for underwater sensor networks with ray compensation is proposed. Besides, the localization algorithm we designed hides the position information of anchor nodes, and eliminates the influence of asynchronous clock. More importantly, the positioning accuracy is improved. Finally, the simulation results show that the location algorithm with privacy preserving and without privacy preserving have the same location accuracy. In addition, the algorithm proposed in this paper greatly improves the positioning accuracy compared with the existing work.

With the increasingly extensive use of diver and unmanned underwater vehicle in military, it has posed a serious threat to the security of the national coastal area. In order to prevent the underwater diver's impact on the safety of water area, it is of great significance to identify underwater small targets in time to make early warning for it. In this paper, convolutional neural network is applied to underwater small target recognition. The recognition targets are diver, whale and dolphin. Due to the time-frequency spectrum can reflect the essential features of underwater target, convolutional neural network can learn a variety of features of the acoustic signal through the image processed by the time-frequency spectrum, time-frequency image is input to convolutional neural network to recognize the underwater small targets. According to the study of learning rate and pooling mode, the network parameters and structure suitable for underwater small target recognition in this paper are selected. The results of data processing show that the method can identify underwater small targets accurately.

An air-gapped computer is physically isolated from unsecured networks to guarantee effective protection against data exfiltration. Due to air gaps, unauthorized data transfer seems impossible over legitimate communication channels, but in reality many so-called physical covert channels can be constructed to allow data exfiltration across the air gaps. Most of such covert channels are very slow and often require certain strict conditions to work (e.g., no physical obstacles between the sender and the receiver). In this paper, we introduce a new physical covert channel named BitJabber that is extremely fast and strong enough to even penetrate concrete walls. We show that this covert channel can be easily created by an unprivileged sender running on a victim’s computer. Specifically, the sender constructs the channel by using only memory accesses to modulate the electromagnetic (EM) signals generated by the DRAM clock. While possessing a very high bandwidth (up to 300,000 bps), this new covert channel is also very reliable (less than 1% error rate). More importantly, this covert channel can enable data exfiltration from an air-gapped computer enclosed in a room with thick concrete walls up to 15 cm.

In the past air-gapped systems that are isolated from networks have been considered to be very secure. Yet there have been reports of such systems being breached. These breaches have shown to use unconventional means for communication also known as covert channels such as Acoustic, Electromagnetic, Magnetic, Electric, Optical, and Thermal to transfer data. In this paper, a review of various attack methods that can compromise an air-gapped system is presented along with a summary of how efficient and dangerous a particular method could be. The capabilities of each covert channel are listed to better understand the threat it poses and also some countermeasures to safeguard against such attack methods are mentioned. These attack methods have already been proven to work and awareness of such covert channels for data exfiltration is crucial in various industries.

Air-gapped networks are isolated from the Internet, since they store and process sensitive information. It has been shown that attackers can exfiltrate data from air-gapped networks by sending acoustic signals generated by computer speakers, however this type of covert channel relies on the existence of loudspeakers in the air-gapped environment. In this paper, we present CD-LEAK - a novel acoustic covert channel that works in constrained environments where loudspeakers are not available to the attacker. Malware installed on a compromised computer can maliciously generate acoustic signals via the optical CD/DVD drives. Binary information can then be modulated over the acoustic signals and be picked up by a nearby Internet connected receiver (e.g., a workstation, hidden microphone, smartphone, laptop, etc.). We examine CD/DVD drives and discuss their acoustical characteristics. We also present signal generation and detection, and data modulation and demodulation algorithms. Based on our proposed method, we developed a transmitter and receiver for PCs and smartphones, and provide the design and implementation details. We examine the channel and evaluate it on various optical drives. We also provide a set of countermeasures against this threat - which has been overlooked.

Mechanical faults of Gas Insulated Switchgear (GIS) often occurred, which may cause serious losses. Detecting vibration signal was effective for condition monitoring and fault diagnosis of GIS. The vibration characteristic of GIS in service was detected and researched based on a developed testing system in this paper, and feature fingerprint extraction method was proposed to evaluate vibration characteristics and diagnose mechanical defects. Through analyzing the spectrum of the vibration signal, we could see that vibration frequency of operating GIS was about 100Hz under normal condition. By means of the wavelet transformation, the vibration fingerprint was extracted for the diagnosis of mechanical vibration. The mechanical vibration characteristic of GIS including circuit breaker and arrester in service was detected, we could see that the frequency distribution of abnormal vibration signal was wider, it contained a lot of high harmonic components besides the 100Hz component, and the vibration acoustic fingerprint was totally different from the normal ones, that is, by comparing the frequency spectra and vibration fingerprint, the mechanical faults of GIS could be found effectively.

Voice user interfaces can offer intuitive interaction with our devices, but the usability and audio quality could be further improved if multiple devices could collaborate to provide a distributed voice user interface. To ensure that users' voices are not shared with unauthorized devices, it is however necessary to design an access management system that adapts to the users' needs. Prior work has demonstrated that a combination of audio fingerprinting and fuzzy cryptography yields a robust pairing of devices without sharing the information that they record. However, the robustness of these systems is partially based on the extensive duration of the recordings that are required to obtain the fingerprint. This paper analyzes methods for robust generation of acoustic fingerprints in short periods of time to enable the responsive pairing of devices according to changes in the acoustic scenery and can be integrated into other typical speech processing tools.