Artificial intelligence technology has been developing rapidly, and speech synthesis models have become increasingly mature, capable of generating highly realistic synthetic audio used to disseminate misinformation, which poses a serious security risk problem. Digital watermarking technology can effectively protect digital content. Deep learning is currently achieving significant research success in digital watermarking. However, the current robustness against audio manipulation remains understudied. Based on this, we propose a robust audio watermarking method based on deep learning against manipulation attacks. Specifically, the embedding of watermarking information is performed in the encoder and the extraction of watermarking information is performed in the decoder; In addition, various audio attacks are simulated during iterative training, a sampling noise layer is used to increase robustness, and a discriminator is used to distinguish between encoded audio and original audio to improve the invisibility of the watermark. We comprehensively evaluate the performance of our model against various manipulation attacks. Experimental results demonstrate that the framework effectively embeds and extracts watermarked signals, exhibiting strong robustness.

Generative AI technologies, including text-to-speech (TTS) and voice conversion (VC), frequently become indistinguishable from genuine samples, posing challenges for individuals in discerning between real and synthetic content. This indistinguishability undermines trust in media, and the arbitrary cloning of personal voice signals presents significant challenges to privacy and security. In the field of deepfake audio detection, the majority of models achieving higher detection accuracy currently employ self-supervised pre-trained models. However, with the ongoing development of deepfake audio generation algorithms, maintaining high discrimination accuracy against new algorithms grows more challenging. To enhance the sensitivity of deepfake audio features, we propose a deepfake audio detection model that incorporates an SLS (Sensitive Layer Selection) module. Specifically, utilizing the pre-trained XLS-R enables our model to extract diverse audio features from its various layers, each providing distinct discriminative information. Utilizing the SLS classifier, our model captures sensitive contextual information across different layer levels of audio features, effectively employing this information for fake audio detection. Experimental results show that our method achieves state-of-the-art (SOTA) performance on both the ASVspoof 2021 DF and In-the-Wild datasets, with a specific Equal Error Rate (EER) of 1.92% on the ASVspoof 2021 DF dataset and 7.46% on the In-the-Wild dataset. Codes and data can be found at https://github.com/QiShanZhang/SLSforADD.

This paper introduces the model structure used in the SVDD 2024 Challenge. The SVDD 2024 challenge has been introduced this year for the first time. Singing voice deepfake detection (SVDD) which faces complexities due to informal speech intonations and varying speech rates. In this paper, we propose the XWSB system, which achieved SOTA performance in the SVDD challenge. XWSB stands for XLS-R, WavLM, and SLS Blend, representing the integration of these technologies for the purpose of SVDD. Specifically, we used the best performing model structure XLS-R&SLS from the ASVspoof DF dataset, and applied SLS to WavLM to form the WavLM&SLS structure. Finally, we integrated two models to form the XWSB system. Experimental results show that our system demonstrates advanced recognition capabilities in the SVDD challenge, specifically achieving an EER of 2.32% in the CtrSVDD track. The code and data can be found at https://github.com/QiShanzhang/XWSB_for_ SVDD2024.

Summary Most of networks in real world obviously present dynamic characteristics over time, and the community structure of adjacent snapshots has a certain degree of instability and temporal smoothing. Traditional Temporal Trade‐off algorithms consider that communities found at time t depend both on past evolutions. Because this kind of algorithms are based on the hypothesis of short‐term smoothness, they can barely find abnormal evolution and group emergence in time. In this paper, a Dynamic Community Detection method based on an improved Evolutionary Matrix (DCDEM) is proposed, and the improved evolutionary matrix combines the community structure detected at the previous time with current network structure to track the evolution. Firstly, the evolutionary matrix transforms original unweighted network into weighted network by incorporating community structure detected at the previous time with current network topology. Secondly, the Overlapping Community Detection based on Edge Density Clustering with New edge Similarity (OCDEDC_NS) algorithm is applied to the evolutionary matrix in order to get edge communities. Thirdly, some small communities are merged to optimize the community structure. Finally, the edge communities are restored to the node overlapping communities. Experiments on both synthetic and real‐world networks demonstrate that the proposed algorithm can detect evolutionary community structure in dynamic networks effectively.

The location of logistics distribution center contains various types of grey information, which can help improve usefulness of the logistics location. In this paper, grey demand and grey production capacity in logistics chain have been discussed, and a optimization model of location with grey demand and grey production capacity is propossed. The model is NP-hard, then a hybrid particle swarm optimization based on grey chance-constrained programming is proposed for it. The example results show that the model and the algorithm can solve the problem of location of logistics distribution center with grey demand and grey production capacity.

The port's throughput prediction is an important part in the port development strategy study. The correct throughput prediction is of significance to the reasonable port layout and transportation planning. On the basis of the development of Fuzhou port, this paper collects the data of Fuzhou port's throughput in 1998-2003, and uses the GM (1,1), the new information GM (1,1) as well as the metabolic GM (1,1) to forecast and compare the Fuzhou port's throughput in 2004-2006.

A grey proposition is first introduced. Based on it, the new definition of a grey set is given from the view point of set theory. The greyness of a grey set indicates the uncertainty of the connotation for a concept. Some properties of grey sets are pointed out. By using the difference information entropy, the grey degree, which quantifies the greyness of a grey set, is got.

Association grey knowledge (in brief spoken of as grey knowledge) is introduced. By making use of difference information entropy, the grey degree which measures the grey characteristics of grey knowledge is given. Some theorems and propositions related to the grey degree and grey characteristics of grey knowledge are obtained. The bigger (or smaller) is the grey degree of grey knowledge, the greater (or lesser) is its grey characteristics, vice versa. It is pointed out that grey knowledge may extend or be transmuted white knowledge.

In this paper, an efficient majority logic optimizer is proposed to synthesize majority gate-based nanoelectronic circuits. A novel sharing and mapping scheme is proposed to achieve simple synthesized circuits and high synthesis speed. The experimental results show that compared to the existing method, the proposed method achieves up to 20% reduction of gate counts and 25% higher synthesis speed. This proposed optimizer can be widely used in quantum cellular automata, tunneling phase logic, and single electron tunneling circuit design

A space-time trellis code with linear transformation (STTC-LT) is presented. The upper bound on the pairwise error probability (PEP) is derived and a new design criterion is proposed. It is shown that the performance of STTC-LT over fast Rayleigh fading channels depends on the weighted square product distance (WSPD). Simulation results are provided for QPSK signal sets. They show that the proposed scheme is superior by about 8 dB and 10 dB to the conventional beamforming and Tarokh-Seshadri-Calderbank codes (TSC) at the bit error rate (BER) of 1.0e-4 over fast fading channels.

A bandwidth allocation scheme for a linear token passing multiplex data bus is proposed based on balancing message transmission time with traffic load to each node. It is proved to provide a network worst case achievable utilization of 50%. Under this allocation scheme, closed-form expressions for the initialized value of token holding timers and token rotation timers in each node are obtained.

A basic and important relation between square wave and sine-cosine function is presented. This relation leads to completely new methods for Fourier analysis and Fourier synthesis.